OTIS Mock AIME 2024–2025Benchmark scores and sources

Published result; benchmark version and evaluation conditions remain in the id and result note.

pillar: math · weight 0.5 within pillar · unit: % (higher is better) · official board ↗
Row Model Result Normalized (0–100) Confidence
1 Qwen3.8 Max 0902 Alibaba / Qwen 100%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Sep 2, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		100.0 40% confidence 40 percent, Low
2 Claude Fable 5 Anthropic 100%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		100.0 100% confidence 100 percent, Full
3 Claude Fable 5.1 Anthropic 100%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Sep 1, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		100.0 100% confidence 100 percent, Full
4 Claude Opus 5.5 Anthropic 100%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Sep 22, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		100.0 100% confidence 100 percent, Full
5 Claude Sonnet 5.5 Anthropic 100%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Sep 29, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		100.0 93% confidence 93 percent, High
6 GPT-5.6 Sol OpenAI 100%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jul 9, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		100.0 100% confidence 100 percent, Full
7 GPT-6 Astra OpenAI 100%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Aug 30, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		100.0 100% confidence 100 percent, Full
8 GPT-6 Sol OpenAI 100%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Sep 22, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		100.0 100% confidence 100 percent, Full
9 GPT-6.1 Sol OpenAI 100%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Sep 29, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		100.0 100% confidence 100 percent, Full
10 Claude Fable 5 Anthropic 99.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jun 10, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		99.7 100% confidence 100 percent, Full
11 GPT-5.6 Terra OpenAI 99.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jul 9, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		99.7 100% confidence 100 percent, Full
12 Qwen3.8 Max Alibaba / Qwen 99.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Aug 4, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		99.4 85% confidence 85 percent, High
13 Muse Spark 1.3 Meta 99.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Sep 17, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		99.2 93% confidence 93 percent, High
14 Grok 4.6 xAI 99.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Aug 14, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		99.2 100% confidence 100 percent, Full
15 Claude Opus 5 Anthropic 98.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jul 24, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		98.9 100% confidence 100 percent, Full
16 Gemini 3.8 Flash Google 98.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Sep 2, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		98.9 100% confidence 100 percent, Full
17 GPT-6 Luna OpenAI 98.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Sep 22, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		98.9 100% confidence 100 percent, Full
18 DeepSeek V4 Pro 0813 DeepSeek 98.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Aug 18, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		98.6 69% confidence 69 percent, Medium
19 Claude Opus 4.8 Anthropic 98.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jun 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		98.3 100% confidence 100 percent, Full
20 GPT-5.6 Luna OpenAI 98.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jul 9, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		98.3 100% confidence 100 percent, Full
21 Grok 4.7 xAI 98.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Sep 22, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		98.1 100% confidence 100 percent, Full
22 Claude Opus 4.7 Anthropic 97.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Apr 17, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		97.8 100% confidence 100 percent, Full
23 Claude Fable 5 Anthropic 97.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		97.8 100% confidence 100 percent, Full
24 Claude Opus 4.8 Anthropic 97.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		97.8 100% confidence 100 percent, Full
25 Claude Opus 5 Anthropic 97.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		97.8 100% confidence 100 percent, Full
26 GPT-5.4 OpenAI 97.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Jul 15, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		97.8 100% confidence 100 percent, Full
27 Grok 4.5 xAI 97.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Jul 8, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		97.8 100% confidence 100 percent, Full
28 Grok 4.6 xAI 97.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Aug 12, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		97.8 100% confidence 100 percent, Full
29 Gemini 3.7 Flash Google 97.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Aug 14, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		97.2 100% confidence 100 percent, Full
30 Kimi K3 Moonshot AI 97.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jul 16, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		97.2 100% confidence 100 percent, Full
31 DeepSeek V4 Pro DeepSeek 96.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jun 17, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		96.7 85% confidence 85 percent, High
32 Kimi K2.6 Moonshot AI 96.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published May 2, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		96.1 85% confidence 85 percent, High
33 GPT-5.2 OpenAI 96.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Dec 11, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		96.1 100% confidence 100 percent, Full
34 GPT-5.2 OpenAI 96.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Dec 13, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		96.1 100% confidence 100 percent, Full
35 Gemini 3.1 Pro Preview Google 95.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 20, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		95.6 100% confidence 100 percent, Full
36 Qwen3.7 Max Alibaba / Qwen 95.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		95.6 53% confidence 53 percent, Medium
37 DeepSeek V4 Pro DeepSeek 95.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		95.6 85% confidence 85 percent, High
38 Gemini 3 Flash Preview Google 95.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		95.6 93% confidence 93 percent, High
39 Gemini 3.1 Pro Preview Google 95.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		95.6 100% confidence 100 percent, Full
40 Gemini 3.5 Flash Google 95.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished May 25, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		95.6 100% confidence 100 percent, Full
41 Kimi K2.7 Code Moonshot AI 95.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		95.6 48% confidence 48 percent, Low
42 GPT-5.4 OpenAI 95.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Jul 15, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		95.6 100% confidence 100 percent, Full
43 GPT-5.6 Sol OpenAI 95.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		95.6 100% confidence 100 percent, Full
44 GPT-5.4 OpenAI 95.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Mar 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		95.3 100% confidence 100 percent, Full
45 Claude Sonnet 5 Anthropic 94.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Jul 1, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		94.7 93% confidence 93 percent, High
46 Claude Opus 4.6 Anthropic 94.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] 64KPublished Feb 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		94.4 100% confidence 100 percent, Full
47 DeepSeek V4 Flash 0731 DeepSeek 94.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Aug 2, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		94.4 69% confidence 69 percent, Medium
48 Gemini 3.6 Flash Google 94.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Aug 2, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		94.2 100% confidence 100 percent, Full
49 GPT-5.2 OpenAI 93.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Dec 11, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		93.9 100% confidence 100 percent, Full
50 GLM-5.3-Flash Z.ai 93.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Aug 26, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		93.9 100% confidence 100 percent, Full
51 Qwen3.6 Plus Alibaba / Qwen 93.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		93.3 80% confidence 80 percent, High
52 Qwen3.7 Plus Alibaba / Qwen 93.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		93.3 64% confidence 64 percent, Medium
53 Claude Opus 5 Anthropic 93.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		93.3 100% confidence 100 percent, Full
54 Kimi K3 Moonshot AI 93.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		93.3 100% confidence 100 percent, Full
55 Grok 4.3 xAI 93.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Jun 17, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		93.3 80% confidence 80 percent, High
56 GLM-5.1 Z.ai 93.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 10, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		93.3 64% confidence 64 percent, Medium
57 Claude Opus 4.6 Anthropic 93.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] 32KPublished Feb 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		93.1 100% confidence 100 percent, Full
58 Gemini 3 Flash Preview Google 92.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Dec 17, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		92.8 93% confidence 93 percent, High
59 Grok 4.20 (Reasoning) xAI 92.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Jul 13, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		92.2 80% confidence 80 percent, High
60 Gemini 3 Pro Preview Google 91.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Nov 19, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		91.4 68% confidence 68 percent, Medium
61 GPT-5 OpenAI 91.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Oct 29, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		91.4 100% confidence 100 percent, Full
62 Qwen3.6 27B Alibaba / Qwen 91.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		91.1 53% confidence 53 percent, Medium
63 Qwen3.6 Max Preview Alibaba / Qwen 91.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		91.1 64% confidence 64 percent, Medium
64 Claude Opus 4.6 Anthropic 91.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		91.1 100% confidence 100 percent, Full
65 GLM-5.3 Z.ai 91.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Aug 24, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		91.1 93% confidence 93 percent, High
66 Inkling Small Thinking Machines Lab 90%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Aug 14, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		90.0 100% confidence 100 percent, Full
67 Qwen3.5 397B-A17B Alibaba / Qwen 88.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		88.9 69% confidence 69 percent, Medium
68 Gemini 3.5 Flash Google 88.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		88.9 100% confidence 100 percent, Full
69 GPT-5.4 mini OpenAI 88.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		88.9 100% confidence 100 percent, Full
70 GPT-5.6 Terra OpenAI 88.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		88.9 100% confidence 100 percent, Full
71 GPT OSS 120B OpenAI 88.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Dec 11, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		88.9 79% confidence 79 percent, Medium
72 Inkling Thinking Machines Lab 88.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Aug 5, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		88.9 100% confidence 100 percent, Full
73 GPT-5.1 OpenAI 88.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Nov 13, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		88.6 85% confidence 85 percent, High
74 DeepSeek Reasoner DeepSeek 87.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Dec 16, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		87.8 32% confidence 32 percent, Low
75 GPT-5.4 nano OpenAI 87.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Apr 14, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		87.8 100% confidence 100 percent, Full
76 GPT-5 OpenAI 87.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Aug 7, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		87.2 100% confidence 100 percent, Full
77 GPT-5.4 mini OpenAI 87.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Apr 15, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		87.2 100% confidence 100 percent, Full
78 Qwen3.5 Plus Alibaba / Qwen 86.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		86.7 32% confidence 32 percent, Low
79 Qwen3.6 35B-A3B Alibaba / Qwen 86.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		86.7 37% confidence 37 percent, Low
80 Qwen3.7 Flash Alibaba / Qwen 86.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		86.7 32% confidence 32 percent, Low
81 Claude Opus 4.7 Anthropic 86.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		86.7 100% confidence 100 percent, Full
82 Nemotron 3 Ultra 550B A55B NVIDIA 86.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 10, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		86.7 100% confidence 100 percent, Full
83 GPT-5 Mini OpenAI 86.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Oct 30, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		86.7 99% confidence 99 percent, High
84 GLM-5.2 Z.ai 86.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jun 25, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		86.4 100% confidence 100 percent, Full
85 Claude Opus 4.5 Anthropic 86.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] 32KPublished Nov 24, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		86.1 100% confidence 100 percent, Full
86 Claude Sonnet 4.6 Anthropic 85.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] 32KPublished Feb 20, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		85.8 100% confidence 100 percent, Full
87 GPT-5.1 OpenAI 85.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Nov 17, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		85.6 85% confidence 85 percent, High
88 Qwen3.5 Flash Alibaba / Qwen 84.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		84.4 64% confidence 64 percent, Medium
89 Qwen3.6 Flash Alibaba / Qwen 84.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		84.4 32% confidence 32 percent, Low
90 Claude Opus 4.8 Anthropic 84.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		84.4 100% confidence 100 percent, Full
91 GPT-5.4 OpenAI 84.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Jul 15, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		84.4 100% confidence 100 percent, Full
92 GPT-5.5 OpenAI 84.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		84.4 100% confidence 100 percent, Full
93 o3 OpenAI 84.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		84.4 87% confidence 87 percent, High
94 Gemini 2.5 Pro Google 84.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Nov 16, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		84.2 90% confidence 90 percent, High
95 o3 OpenAI 83.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Apr 16, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		83.9 87% confidence 87 percent, High
96 GLM-4.7 Z.ai 83.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Jan 29, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		83.3 69% confidence 69 percent, Medium
97 Kimi K2 Thinking Turbo Moonshot AI 83.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Nov 13, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		83.1 64% confidence 64 percent, Medium
98 Qwen3.5 397B-A17B Alibaba / Qwen 82.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		82.2 69% confidence 69 percent, Medium
99 Claude Sonnet 4.6 Anthropic 82.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Jul 13, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		82.2 100% confidence 100 percent, Full
100 Gemini 3.6 Flash Google 82.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		82.2 100% confidence 100 percent, Full
101 Gemma 4 26B A4B IT Google 82.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] minimalPublished Aug 28, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		82.2 64% confidence 64 percent, Medium
102 Claude Opus 4.5 Anthropic 81.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] 16KPublished Nov 24, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		81.7 100% confidence 100 percent, Full
103 o4-mini OpenAI 81.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Apr 16, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		81.7 87% confidence 87 percent, High
104 GPT-5 Nano OpenAI 81.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Oct 31, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		81.1 85% confidence 85 percent, High
105 Qwen3.7 Plus Alibaba / Qwen 80%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		80.0 64% confidence 64 percent, Medium
106 Claude Sonnet 5 Anthropic 80%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		80.0 93% confidence 93 percent, High
107 Gemini 3.1 Flash Lite Google 80%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		80.0 32% confidence 32 percent, Low
108 Gemini 3.5 Flash Google 80%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] minimalPublished Jul 15, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		80.0 100% confidence 100 percent, Full
109 Gemini 3.6 Flash Google 80%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] minimalPublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		80.0 100% confidence 100 percent, Full
110 GLM-5 Z.ai 80%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 12, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		80.0 90% confidence 90 percent, High
111 GPT-5.2 OpenAI 78.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Dec 11, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		78.9 100% confidence 100 percent, Full
112 GPT-5 Mini OpenAI 78.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Aug 7, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		78.3 99% confidence 99 percent, High
113 Qwen3.7 Flash Alibaba / Qwen 77.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		77.8 32% confidence 32 percent, Low
114 Claude Sonnet 4.5 Anthropic 77.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] 32KPublished Oct 21, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		77.8 80% confidence 80 percent, High
115 Claude Sonnet 4.5 Anthropic 77.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] 59KPublished Oct 28, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		77.8 80% confidence 80 percent, High
116 Claude Sonnet 4.6 Anthropic 75.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Jul 13, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		75.6 100% confidence 100 percent, Full
117 GLM-5.2 Z.ai 75.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 10, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		75.6 100% confidence 100 percent, Full
118 GPT-5 Nano OpenAI 74.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Aug 7, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		74.2 85% confidence 85 percent, High
119 Qwen3 Max Alibaba / Qwen 73.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Oct 6, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		73.3 69% confidence 69 percent, Medium
120 Gemma 4 31B IT Google 73.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] minimalPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		73.3 64% confidence 64 percent, Medium
121 o4-mini OpenAI 73.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		73.3 87% confidence 87 percent, High
122 Claude Sonnet 4 Anthropic 71.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] 32KPublished May 22, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		71.1 100% confidence 100 percent, Full
123 Claude Sonnet 4.5 Anthropic 71.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] 16KPublished Oct 28, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		71.1 80% confidence 80 percent, High
124 Claude Sonnet 4.6 Anthropic 71.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		71.1 100% confidence 100 percent, Full
125 Gemini 3.5 Flash Lite Google 71.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		71.1 100% confidence 100 percent, Full
126 MiniMax-M3 MiniMax 71.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 10, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		71.1 100% confidence 100 percent, Full
127 Qwen3.5 35B-A3B Alibaba / Qwen 70%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 30, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		70.0 64% confidence 64 percent, Medium
128 Qwen3.6 35B-A3B Alibaba / Qwen 68.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		68.9 37% confidence 37 percent, Low
129 Claude Opus 4.1 Anthropic 68.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] 27KPublished Aug 5, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		68.9 80% confidence 80 percent, High
130 Claude Sonnet 4 Anthropic 68.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] 59KPublished May 23, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		68.9 100% confidence 100 percent, Full
131 Kimi K3 Moonshot AI 68.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		68.9 100% confidence 100 percent, Full
132 GPT-5.4 nano OpenAI 68.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		68.9 100% confidence 100 percent, Full
133 GPT-5.6 Sol OpenAI 68.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		68.9 100% confidence 100 percent, Full
134 GPT-5.5 Instant OpenAI 68.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 2, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		68.1 64% confidence 64 percent, Medium
135 Qwen3 32B Alibaba / Qwen 66.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 30, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		66.9 67% confidence 67 percent, Medium
136 Qwen3.6 27B Alibaba / Qwen 66.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		66.7 53% confidence 53 percent, Medium
137 Claude Haiku 4.5 Anthropic 66.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] 32KPublished Oct 22, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		66.7 64% confidence 64 percent, Medium
138 GPT-5.6 Luna OpenAI 66.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		66.7 100% confidence 100 percent, Full
139 DeepSeek-R1 DeepSeek 66.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published May 29, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		66.4 88% confidence 88 percent, High
140 GPT OSS 20B OpenAI 65.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Aug 27, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		65.3 64% confidence 64 percent, Medium
141 Claude Opus 4.1 Anthropic 64.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] 16KPublished Aug 5, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		64.4 80% confidence 80 percent, High
142 Claude Opus 4 Anthropic 64.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] 27KPublished May 28, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		64.4 100% confidence 100 percent, Full
143 GPT-5.1 OpenAI 63.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Nov 25, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		63.9 85% confidence 85 percent, High
144 Qwen3 30B A3B Alibaba / Qwen 62.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 28, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		62.8 64% confidence 64 percent, Medium
145 GPT-5.2 OpenAI 62.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Jul 13, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		62.2 100% confidence 100 percent, Full
146 Qwen3.5 9B Alibaba / Qwen 61.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 27, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		61.7 32% confidence 32 percent, Low
147 Claude Opus 4 Anthropic 60%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] 16KPublished May 22, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		60.0 100% confidence 100 percent, Full
148 Gemini 3.5 Flash Lite Google 60%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		60.0 100% confidence 100 percent, Full
149 o3 OpenAI 60%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Jul 15, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		60.0 87% confidence 87 percent, High
150 QwQ 32B Alibaba / Qwen 59.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 28, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		59.2 67% confidence 67 percent, Medium
151 GLM-4.7-Flash Z.ai 58.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 30, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		58.3 69% confidence 69 percent, Medium
152 Claude Sonnet 3.7 Anthropic 57.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] 64KPublished Mar 13, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		57.8 100% confidence 100 percent, Full
153 GPT-5.4 OpenAI 57.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Jul 15, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		57.8 100% confidence 100 percent, Full
154 GPT-5.5 OpenAI 57.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		57.8 100% confidence 100 percent, Full
155 o4-mini OpenAI 57.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Jul 13, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		57.8 87% confidence 87 percent, High
156 DeepSeek-R1-Distill-Qwen-32B DeepSeek 55.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 28, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		55.6 32% confidence 32 percent, Low
157 GPT-5 Mini OpenAI 55.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] minimalPublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		55.6 99% confidence 99 percent, High
158 Qwen3.5 35B-A3B Alibaba / Qwen 54.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 30, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		54.4 64% confidence 64 percent, Medium
159 Claude Sonnet 3.7 Anthropic 53.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] 32KPublished Mar 12, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		53.3 100% confidence 100 percent, Full
160 Claude Sonnet 4 Anthropic 53.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] 16KPublished May 22, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		53.3 100% confidence 100 percent, Full
161 GPT-5.6 Terra OpenAI 53.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		53.3 100% confidence 100 percent, Full
162 Gemini 3.5 Flash Lite Google 51.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] minimalPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		51.1 100% confidence 100 percent, Full
163 GPT OSS 20B OpenAI 50.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Aug 27, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		50.8 64% confidence 64 percent, Medium
164 DeepSeek Chat DeepSeek 48.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Jul 16, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		48.9 32% confidence 32 percent, Low
165 Claude Opus 4.5 Anthropic 48.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Nov 24, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		48.1 100% confidence 100 percent, Full
166 Claude Sonnet 3.7 Anthropic 46.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] 16KPublished Feb 26, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		46.7 100% confidence 100 percent, Full
167 DeepSeek V4 Pro DeepSeek 46.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		46.7 85% confidence 85 percent, High
168 GPT-5 OpenAI 46.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] minimalPublished Jul 20, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		46.7 100% confidence 100 percent, Full
169 GPT-5 Nano OpenAI 46.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Jul 13, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		46.7 85% confidence 85 percent, High
170 GPT-5.4 nano OpenAI 46.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		46.7 100% confidence 100 percent, Full
171 GPT-4.1 mini OpenAI 44.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Apr 14, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		44.7 87% confidence 87 percent, High
172 Gemini 3.1 Flash Lite Google 44.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		44.4 32% confidence 32 percent, Low
173 Qwen3.5 9B Alibaba / Qwen 42.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 27, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		42.8 32% confidence 32 percent, Low
174 Claude Opus 4 Anthropic 42.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published May 22, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		42.2 100% confidence 100 percent, Full
175 GPT OSS 20B OpenAI 40.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 27, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		40.3 64% confidence 64 percent, Medium
176 Claude Opus 4.1 Anthropic 40%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 5, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		40.0 80% confidence 80 percent, High
177 GPT-5.6 Luna OpenAI 40%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		40.0 100% confidence 100 percent, Full
178 GPT-4.1 OpenAI 38.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Apr 14, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		38.3 100% confidence 100 percent, Full
179 DeepSeek V3 0324 DeepSeek 37.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Apr 1, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		37.8 74% confidence 74 percent, Medium
180 Gemini 3.1 Flash Lite Google 37.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] minimalPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		37.8 32% confidence 32 percent, Low
181 GPT-5.1 OpenAI 37.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		37.8 85% confidence 85 percent, High
182 Claude Haiku 4.5 Anthropic 35.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Oct 16, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		35.8 64% confidence 64 percent, Medium
183 Claude Sonnet 4.5 Anthropic 35.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Sep 29, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		35.6 80% confidence 80 percent, High
184 GPT-5 Nano OpenAI 35.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] minimalPublished Jul 13, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		35.6 85% confidence 85 percent, High
185 Mistral Medium 3 Mistral AI 32.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published May 7, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		32.2 85% confidence 85 percent, High
186 Magistral Small Mistral AI 30%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		30.0 48% confidence 48 percent, Low
187 Claude Sonnet 4 Anthropic 28.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published May 22, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		28.9 100% confidence 100 percent, Full
188 GPT-4.1 nano OpenAI 28.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Apr 14, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		28.9 82% confidence 82 percent, High
189 GLM-5.2 Z.ai 28.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 10, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		28.9 100% confidence 100 percent, Full
190 Magistral Small 1.2 Mistral AI 28.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 30, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		28.1 32% confidence 32 percent, Low
191 MiniMax-M3 MiniMax 26.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 10, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		26.7 100% confidence 100 percent, Full
192 GPT-5.4 mini OpenAI 26.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		26.7 100% confidence 100 percent, Full
193 Qwen3 30B A3B Alibaba / Qwen 25.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 30, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		25.6 64% confidence 64 percent, Medium
194 GLM-4.7-Flash Z.ai 25%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 28, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		25.0 69% confidence 69 percent, Medium
195 Qwen3 32B Alibaba / Qwen 23.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 30, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		23.1 67% confidence 67 percent, Medium
196 Gemma 3 27B IT Google 22.5%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 27, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		22.5 74% confidence 74 percent, Medium
197 Claude Sonnet 3.7 Anthropic 21.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 25, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		21.9 100% confidence 100 percent, Full
198 Llama 4 Maverick 17B Instruct Meta 20.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Apr 8, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		20.6 78% confidence 78 percent, Medium
199 Gemma 3 12B IT Google 16.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 28, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		16.7 64% confidence 64 percent, Medium
200 DeepSeek-V3 DeepSeek 15.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 25, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		15.8 93% confidence 93 percent, High
201 Claude Sonnet 3.5 v2 Anthropic 8.5%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 25, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		8.5 100% confidence 100 percent, Full
202 Llama 4 Scout 17B Instruct Meta 7.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Apr 8, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		7.8 64% confidence 64 percent, Medium
203 Mistral Large 2.1 Mistral AI 7.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 25, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		7.8 100% confidence 100 percent, Full
204 Gemma 3 4B IT Google 7.5%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 28, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		7.5 64% confidence 64 percent, Medium
205 GPT-4o mini OpenAI 6.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Jul 30, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		6.9 100% confidence 100 percent, Full
206 GPT-4o (2024-08-06) OpenAI 6.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 25, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		6.4 100% confidence 100 percent, Full
207 GPT-4o (2024-05-13) OpenAI 6.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 25, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		6.3 93% confidence 93 percent, High
208 GPT-4o (2024-11-20) OpenAI 6.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 25, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		6.3 61% confidence 61 percent, Medium
209 Qwen Turbo Alibaba / Qwen 6.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Apr 7, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		6.1 47% confidence 47 percent, Low
210 Mistral Small 3.1 24B Mistral AI 5.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Mar 18, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		5.8 64% confidence 64 percent, Medium
211 Llama-3.3-70B-Instruct Meta 5.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 25, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		5.1 100% confidence 100 percent, Full
212 Claude Haiku 3.5 Anthropic 4.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 25, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		4.3 100% confidence 100 percent, Full
213 Llama-3.1-70B-Instruct Meta 3.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 25, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		3.6 93% confidence 93 percent, High
214 Claude Haiku 3 Anthropic 1.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 25, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		1.8 93% confidence 93 percent, High
215 Llama-3.1-8B-Instruct Meta 1.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 27, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		1.7 93% confidence 93 percent, High
216 Llama-3.2-1B Meta 0.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 30, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		0.6 93% confidence 93 percent, High

Results are as published by the source behind each value (hover or tap the number). Benchmark scores are shown individually for every source/variant (a model may have multiple rows), and vary by version, harness and date; the normalized column uses the method’s fixed 0–100 scales and feeds the math pillar of the SI Score.

What changed

All releases · RSS feed

Alerts on this device

What to be alerted about
RSS feed