Claude Opus 5vsClaude Fable 5.1
SI Score, benchmarks, price and context compared, with every number sourced.
79.6
SI Score
#4 of 124 ranked models
79.4
SI Score
#6 of 124 ranked models
Pillar by pillar
Claude Opus 5Claude Fable 5.1
83.2 Reasoning25% of score 78.9
86.7 Math25% of score 92.3
66.7 Coding25% of score 63.9
82.0 Preference25% of score 82.5
The basics
| Attribute | Claude Opus 5 | Claude Fable 5.1 |
|---|---|---|
| Input price, per 1M tokens | $5.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | $10.00Anthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ |
| Output price, per 1M tokens | $25.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | $50.00Anthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ |
| Context window | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1MAnthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ |
| Released | Jul 24, 2026models.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Sep 1, 2026Anthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ |
| Weights | Closed | Closed |
Highlighted values are the lower price or the larger context window.
Shared benchmarks
27 in common. Best result ahead: Claude Opus 5 on 4, Claude Fable 5.1 on 16Each side shows its best published result. Results can come from different settings or harnesses, so open a row to compare like with like before reading much into a small gap.
ARC-AGI-1 (public eval) 99% 99%
Claude Opus 5
- high effort99%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' output effort. [variant] anthropic-claude-opus-5-highPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - max effort99%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' output effort. [variant] anthropic-claude-opus-5-maxPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗
Claude Fable 5.1
- low effort95.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort. [variant] anthropic-claude-fable-5-1-lowPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - medium effort96.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort. [variant] anthropic-claude-fable-5-1-mediumPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - high effort97.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort. [variant] anthropic-claude-fable-5-1-highPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - xhigh effort98.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort. [variant] anthropic-claude-fable-5-1-xhighPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - max effort99%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort. [variant] anthropic-claude-fable-5-1-maxPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗
ARC-AGI-1 (semi-private) 97.5% 97.5%
Claude Opus 5
- high effort97.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' output effort. [variant] anthropic-claude-opus-5-highPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - max effort97.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' output effort. [variant] anthropic-claude-opus-5-maxPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗
Claude Fable 5.1
- low effort90%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort. [variant] anthropic-claude-fable-5-1-lowPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - medium effort94.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort. [variant] anthropic-claude-fable-5-1-mediumPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - high effort96%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort. [variant] anthropic-claude-fable-5-1-highPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - xhigh effort96.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort. [variant] anthropic-claude-fable-5-1-xhighPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - max effort97.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort. [variant] anthropic-claude-fable-5-1-maxPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗
ARC-AGI-2 (public eval) 97.1% 99.2%
Claude Opus 5
- high effort93.2%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' output effort. [variant] anthropic-claude-opus-5-highPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - max effort97.1%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' output effort. [variant] anthropic-claude-opus-5-maxPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗
Claude Fable 5.1
- low effort86.0%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort. [variant] anthropic-claude-fable-5-1-lowPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - medium effort87.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort. [variant] anthropic-claude-fable-5-1-mediumPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - high effort94.7%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort. [variant] anthropic-claude-fable-5-1-highPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - xhigh effort99.2%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort. [variant] anthropic-claude-fable-5-1-xhighPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - max effort98.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort. [variant] anthropic-claude-fable-5-1-maxPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗
ARC-AGI-2 (semi-private) 90.4% 90%
Claude Opus 5
- high effort88.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' output effort. [variant] anthropic-claude-opus-5-highPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - max effort90.4%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' output effort. [variant] anthropic-claude-opus-5-maxPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗
Claude Fable 5.1
- low effort78.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort. [variant] anthropic-claude-fable-5-1-lowPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - medium effort86.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort. [variant] anthropic-claude-fable-5-1-mediumPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - high effort88.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort. [variant] anthropic-claude-fable-5-1-highPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - xhigh effort90%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort. [variant] anthropic-claude-fable-5-1-xhighPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - max effort90%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort. [variant] anthropic-claude-fable-5-1-maxPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗
FrontierMath Tier 4 (v2) 73.2% 87.8%
Claude Opus 5
- max effort73.2%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 ↗
Claude Fable 5.1
- max effort87.8%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 ↗
FrontierMath Tiers 1–3 (v2) 85.6% 90.2%
Claude Opus 5
- max effort85.6%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 ↗
Claude Fable 5.1
- max effort90.2%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 ↗
Humanity's Last Exam 56.3% 60.9%
Claude Opus 5
- Published result56.3%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] no toolsPublished Jul 24, 2026
Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗
Claude Fable 5.1
- Published result60.9%Official model cards via models.devLab-reported; metric score; transcribed by MIT models.dev catalog; not independently evaluated [variant] without tools; production safeguards with fallbackPublished Sep 1, 2026
Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗
Humanity's Last Exam (with tools) 64.7% 65%
Claude Opus 5
- Published result64.7%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] with toolsPublished Jul 24, 2026
Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗
Claude Fable 5.1
- Published result65%Official model cards via models.devLab-reported; metric score; transcribed by MIT models.dev catalog; not independently evaluated [variant] with tools; production safeguards with fallbackPublished Sep 1, 2026
Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗
LiveBench Coding: code completion 82.6% 82.6%
Claude Opus 5
- Published result82.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
Claude Fable 5.1
- Published result82.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Coding: code generation 80.3% 90.1%
Claude Opus 5
- Published result80.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
Claude Fable 5.1
- Published result90.1%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Coding: JavaScript 77.3% 68.2%
Claude Opus 5
- Published result77.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
Claude Fable 5.1
- Published result68.2%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Coding: Python 75% 70%
Claude Opus 5
- Published result75%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
Claude Fable 5.1
- Published result70%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Coding: TypeScript 43.3% 60%
Claude Opus 5
- Published result43.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
Claude Fable 5.1
- Published result60%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Math: AMPS Hard 99.0% 99%
Claude Opus 5
- Published result99.0%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
Claude Fable 5.1
- Published result99%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Math: competition math 94.1% 97.1%
Claude Opus 5
- Published result94.1%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
Claude Fable 5.1
- Published result97.1%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Math: integrals 97% 99%
Claude Opus 5
- Published result97%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
Claude Fable 5.1
- Published result99%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Math: olympiad 92.8% 93.0%
Claude Opus 5
- Published result92.8%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
Claude Fable 5.1
- Published result93.0%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Math: simplify 61.6% 70.2%
Claude Opus 5
- Published result61.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
Claude Fable 5.1
- Published result70.2%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Reasoning: connections 99.3% 99.3%
Claude Opus 5
- Published result99.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
Claude Fable 5.1
- Published result99.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Reasoning: consecutive events 77.6% 90.6%
Claude Opus 5
- Published result77.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
Claude Fable 5.1
- Published result90.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Reasoning: logic with navigation 86% 86%
Claude Opus 5
- Published result86%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
Claude Fable 5.1
- Published result86%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Reasoning: spatial 100% 100%
Claude Opus 5
- Published result100%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
Claude Fable 5.1
- Published result100%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Reasoning: theory of mind 78.8% 80.8%
Claude Opus 5
- Published result78.8%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
Claude Fable 5.1
- Published result80.8%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Reasoning: zebra puzzles 100% 100%
Claude Opus 5
- Published result100%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
Claude Fable 5.1
- Published result100%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LMArena Text 1502.6 elo 1510.0 elo
Claude Opus 5
- Published result1502.6 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 8, 2026
Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗
Claude Fable 5.1
- Published result1510.0 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 8, 2026
Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗
OTIS Mock AIME 2024–2025 98.9% 100%
Claude Opus 5
- low effort93.3%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 ↗ - max effort98.9%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 ↗ - Setting 397.8%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 ↗
Claude Fable 5.1
- max effort100%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 ↗
Terminal-Bench 4.0 53.9% 57.9%
Claude Opus 5
- Setting 153.9%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; xhighPublished Sep 17, 2026
Retrieved Oct 9, 2026 · Apache-2.0; factual citation
Open source ↗ - Setting 251.8%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; maxPublished Sep 3, 2026
Retrieved Oct 9, 2026 · Apache-2.0; factual citation
Open source ↗ - Setting 350.3%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; highPublished Sep 17, 2026
Retrieved Oct 9, 2026 · Apache-2.0; factual citation
Open source ↗ - Setting 444.9%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; mediumPublished Sep 17, 2026
Retrieved Oct 9, 2026 · Apache-2.0; factual citation
Open source ↗ - Setting 534.9%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; lowPublished Sep 17, 2026
Retrieved Oct 9, 2026 · Apache-2.0; factual citation
Open source ↗
Claude Fable 5.1
- Setting 157.9%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; maxPublished Sep 3, 2026
Retrieved Oct 9, 2026 · Apache-2.0; factual citation
Open source ↗ - Setting 257.9%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; xhighPublished Sep 17, 2026
Retrieved Oct 9, 2026 · Apache-2.0; factual citation
Open source ↗ - Setting 355.8%Official model cards via models.devLab-reported; metric score; transcribed by MIT models.dev catalog; not independently evaluated [variant] production safeguards with fallback; 4.0Published Sep 1, 2026
Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ - Setting 454.5%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; highPublished Sep 17, 2026
Retrieved Oct 9, 2026 · Apache-2.0; factual citation
Open source ↗ - Setting 553.9%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; mediumPublished Sep 17, 2026
Retrieved Oct 9, 2026 · Apache-2.0; factual citation
Open source ↗ - Setting 643.3%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; lowPublished Sep 17, 2026
Retrieved Oct 9, 2026 · Apache-2.0; factual citation
Open source ↗
Which should you choose?
- For reasoning, Claude Opus 5 leads by 4.3 points.
- For math, Claude Fable 5.1 leads by 5.6 points.
- Claude Opus 5 costs less per input token ($5.00 vs $10.00 per 1M).
- Confidence is 100% for Claude Opus 5 and 100% for Claude Fable 5.1; sources still to report can move either score.
These follow from the numbers above. They're not a verdict on your use case.