New releasesNew AI and super intelligence model releases, newest first

Newest releases first. A new model goes live as soon as its identity and a primary source are confirmed. Scores fill in as benchmark publishers and the lab report results.

392 text-model releases tracked Updated Oct 9, 2026 RSS feed

October 20262 releases

Oct 7 Claude Haiku 5.5 Anthropic 59.4#64 Source
Oct 6 Mistral Large 4 Mistral AI 62.2#53 Source

September 202626 releases

Sep 29 Ling 3.1 Flash inclusionAI Awaiting results Source
Sep 29 GPT-6.1 Sol OpenAI 73.0#6 Source
Sep 28 Claude Sonnet 5.5 Anthropic 69.4#15 Source
Sep 27 MiniMax-M3.1-Flash-Preview MiniMax Awaiting results Source
Sep 25 LongCat-2.5-Preview Meituan Awaiting results Source
Sep 23 Qwen 3.8 Max Prime Alibaba / Qwen Awaiting results Source
Sep 22 Claude Opus 5.5 Anthropic 78.4#2 Source
Sep 22 GPT-6 Luna OpenAI 61.6#55 Source
Sep 22 GPT-6 Sol OpenAI 68.9#16 Source
Sep 22 MiMo-V2.6-Flash XiaomiOpen weights 55.8#81 Source
Sep 22 MiMo-V2.6-Pro XiaomiOpen weights 57.4#74 Source
Sep 21 Viv Fast Vivgrid Awaiting results Source
Sep 21 Grok 4.7 xAI 65.5#36 Source
Sep 21 MiMo-V2.6-Pro-UltraSpeed XiaomiOpen weights Awaiting results Source
Sep 17 Qwen3.8 Omni Flash Alibaba / Qwen Awaiting results Source
Sep 17 Pareto Unbiased Awaiting results Source
Sep 16 Step 5 Preview StepFun 54.1 Source
Sep 11 Kimi K2.8 Preview Moonshot AI Awaiting results Source
Sep 10 DeepSeek V4.1 Flash DeepSeekOpen weights 66.2#31 Source
Sep 6 MiniCPM5-2B OpenBMBOpen weights Awaiting results Source
Sep 4 GPT-6 Astra (Fast) OpenAI Awaiting results Source
Sep 3 GPT-6 Astra OpenAI 77.5#3 Source
Sep 2 Qwen3.8 Max 0902 Alibaba / Qwen 51.9 Source
Sep 2 Gemini 3.8 Flash Google 68.8#17 Source
Sep 2 Muse Spark 1.3 Meta 70.1#11 Source
Sep 1 Claude Fable 5.1 Anthropic 80.2#1 Source

August 202624 releases

Aug 28 Hy4 preview TencentOpen weights Awaiting results Source
Aug 27 Qwen3.8 Flash Next Alibaba / QwenOpen weights 54.3 Source
Aug 27 Ling 3.0 Flash Fin inclusionAI Awaiting results Source
Aug 26 Qwen3.8 Flash Alibaba / Qwen Awaiting results Source
Aug 26 GLM-5.3-Flash Z.aiOpen weights 66.2#30 Source
Aug 21 DeepSeek V4 Flash Vision Exp DeepSeekOpen weights 54.8 Source
Aug 18 Ornith 1.5 35B A3B DeepReinforceOpen weights Awaiting results Source
Aug 14 Qwen3.8 27B Alibaba / QwenOpen weights 61.9#54 Source
Aug 14 GLM-5.3 Z.aiOpen weights 67.7#24 Source
Aug 13 Gemini 3.7 Flash Google 70.0#12 Source
Aug 13 Toast 1 Mixedbread Awaiting results Source
Aug 12 Qwen3.8 2.4T A95B Alibaba / QwenOpen weights Awaiting results Source
Aug 12 DeepSeek V4 Pro 0813 DeepSeekOpen weights 63.0#46 Source
Aug 12 Grok 4.6 xAI 66.6#27 Source
Aug 11 MAI-Code-1.1-Flash Microsoft Awaiting results Source
Aug 11 Nemotron 3.5 Lightning 30B A3B NVIDIAOpen weights 46.1#116 Source
Aug 10 Muse Glimmer 30B MetaOpen weights 50.9 Source
Aug 7 Motif 3 Motif TechnologiesOpen weights Awaiting results Source
Aug 7 GPT-5.6 Cyber OpenAI Awaiting results Source
Aug 6 Solar Pro 4 Upstage 53.3 Source
Aug 5 Muse Spark 1.2 Meta 62.3#52 Source
Aug 4 Grok Voice STT 1.0 xAI Awaiting results Source
Aug 3 Qwen3.8 Max Alibaba / Qwen 68.7#18 Source
Aug 3 Sakana Namazu Sakana AI 53.5 Source

July 202617 releases

Jul 31 DeepSeek V4 Flash 0731 DeepSeekOpen weights 61.0#60 Source
Jul 30 Inkling Small Thinking Machines LabOpen weights 53.6#95 Source
Jul 24 Claude Opus 5 Anthropic 74.9#5 Source
Jul 21 Gemini 3.5 Flash Lite Google 55.2#89 Source
Jul 21 Gemini 3.6 Flash Google 65.5#35 Source
Jul 21 Gemini Flash-Lite Latest Google Awaiting results Source
Jul 21 Laguna S 2.1 PoolsideOpen weights Awaiting results Source
Jul 19 Qwen3.8 Max Preview Alibaba / Qwen 50.9 Source
Jul 16 Kimi K3 Moonshot AIOpen weights 71.0#9 Source
Jul 15 Qwen3.7 Flash Alibaba / Qwen 54.5 Source
Jul 15 Inkling Thinking Machines LabOpen weights 66.5#28 Source
Jul 9 GPT-5.6 Luna OpenAI 63.4#41 Source
Jul 9 GPT-5.6 Sol OpenAI 72.1#7 Source
Jul 9 GPT-5.6 Terra OpenAI 68.2#21 Source
Jul 8 Grok 4.5 xAI 64.8#37 Source
Jul 6 Hy3 TencentOpen weights 60.7#61 Source
Jul 2 Laguna XS 2.1 PoolsideOpen weights 50.5 Source

June 202627 releases

Jun 30 Claude Sonnet 5 Anthropic 67.7#25 Source
Jun 30 LongCat-2.0 Meituan 56.6#77 Source
Jun 25 Ornith 1.0 31B DeepReinforceOpen weights Awaiting results Source
Jun 25 Ornith 1.0 35B DeepReinforceOpen weights 53.5 Source
Jun 25 Ornith 1.0 397B DeepReinforceOpen weights 56.3 Source
Jun 25 Ornith 1.0 9B DeepReinforceOpen weights 50.4 Source
Jun 23 Seed 2.1 Pro ByteDance Seed Awaiting results Source
Jun 23 Seed 2.1 Turbo ByteDance Seed Awaiting results Source
Jun 23 Seed Character ByteDance Seed Awaiting results Source
Jun 23 Seed Evolving ByteDance Seed Awaiting results Source
Jun 15 Fugu Sakana AI 55.9#80 Source
Jun 15 Fugu Ultra Sakana AI 57.9#71 Source
Jun 13 GLM-5.2 Z.aiOpen weights 65.7#34 Source
Jun 12 Kimi K2.7 Code Moonshot AIOpen weights 56.3 Source
Jun 12 Kimi K2.7 Code Highspeed Moonshot AIOpen weights Awaiting results Source
Jun 9 Claude Fable 5 Anthropic 76.8#4 Source
Jun 9 Claude Mythos 5 Anthropic 51.7 Source
Jun 9 North Mini Code CohereOpen weights 50.4 Source
Jun 9 DiffusionGemma 26B A4B IT GoogleOpen weights Awaiting results Source
Jun 9 Gemma 4 12B IT GoogleOpen weights Awaiting results Source
Jun 8 MiMo-V2.5-Pro-UltraSpeed XiaomiOpen weights Awaiting results Source
Jun 4 Nemotron 3 Ultra 550B A55B NVIDIAOpen weights 61.2#59 Source
Jun 4 Nemotron 3.5 Content Safety NVIDIAOpen weights Awaiting results Source
Jun 2 Qwen3.7 Plus Alibaba / Qwen 62.7#48 Source
Jun 2 MAI-Code-1-Flash Microsoft 50.1 Source
Jun 2 Nex-N2-Pro Nex AGIOpen weights Awaiting results Source
Jun 1 MiniMax-M3 MiniMaxOpen weights 68.0#23 Source

May 20269 releases

May 29 Step 3.7 Flash StepFunOpen weights 50.3 Source
May 28 Claude Opus 4.8 Anthropic 67.5#26 Source
May 21 Qwen3.7 Max Alibaba / Qwen 58.6#67 Source
May 20 Command A Plus CohereOpen weights Awaiting results Source
May 19 Gemini 3.5 Flash Google 68.3#19 Source
May 19 Gemini Flash Latest Google Awaiting results Source
May 19 MiniCPM5-1B OpenBMBOpen weights Awaiting results Source
May 7 Gemini 3.1 Flash Lite Google 53.2 Source
May 5 GPT-5.5 Instant OpenAI 58.3#69 Source

April 202631 releases

Apr 29 Mistral Medium 3.5 Mistral AIOpen weights 58.1 Source
Apr 29 Mistral Medium (latest) Mistral AIOpen weights 51.2 Source
Apr 28 Nemotron 3 Nano Omni 30B A3B Reasoning NVIDIAOpen weights Awaiting results Source
Apr 28 Laguna M.1 PoolsideOpen weights Awaiting results Source
Apr 28 Laguna XS.2 PoolsideOpen weights Awaiting results Source
Apr 27 Qwen3.6 Flash Alibaba / Qwen 54.9 Source
Apr 24 DeepSeek V4 Flash DeepSeekOpen weights 56.2#79 Source
Apr 24 DeepSeek V4 Pro DeepSeekOpen weights 63.1#44 Source
Apr 24 GPT-5.5 OpenAI 69.5#14 Source
Apr 24 GPT-5.5 Pro OpenAI 63.5#40 Source
Apr 22 Qwen3.6 27B Alibaba / QwenOpen weights 55.6#86 Source
Apr 22 MiMo-V2.5 XiaomiOpen weights 56.4#78 Source
Apr 22 MiMo-V2.5-Pro XiaomiOpen weights 62.6#51 Source
Apr 21 Kimi K2.6 Moonshot AIOpen weights 64.0#38 Source
Apr 20 Qwen3.6 Max Preview Alibaba / Qwen 66.4#29 Source
Apr 20 Hy3 preview TencentOpen weights 52.1 Source
Apr 17 Qwen3.6 35B-A3B Alibaba / QwenOpen weights 56.3 Source
Apr 17 Grok 4.3 xAI 54.6#92 Source
Apr 16 Claude Opus 4.7 Anthropic 71.2#8 Source
Apr 16 Nemotron 3 Content Safety NVIDIAOpen weights Awaiting results Source
Apr 16 Grok Build 0.1 xAI 52.0 Source
Apr 8 Muse Spark 1.1 Meta 62.9#47 Source
Apr 7 GLM-5.1 Z.aiOpen weights 63.3#43 Source
Apr 2 Qwen3.6 Plus Alibaba / Qwen 61.6#56 Source
Apr 2 Gemma 4 26B A4B IT GoogleOpen weights 63.4#42 Source
Apr 2 Gemma 4 31B IT GoogleOpen weights 63.0#45 Source
Apr 2 Gemma 4 E2B IT GoogleOpen weights Awaiting results Source
Apr 2 Gemma 4 E4B IT GoogleOpen weights Awaiting results Source
Apr 2 Step 3.5 Flash 2603 StepFunOpen weights 48.5 Source
Apr 1 Trinity Large Thinking Arcee AIOpen weights 52.5 Source
Apr 1 GLM-5V-Turbo Z.ai 54.0 Source

March 202619 releases

Mar 31 Llama Nemotron Rerank VL 1B v2 NVIDIAOpen weights Awaiting results Source
Mar 24 Nemotron Cascade 2 30B A3B NVIDIAOpen weights Awaiting results Source
Mar 18 MiniMax-M2.7 MiniMaxOpen weights 57.9#70 Source
Mar 18 MiniMax-M2.7-highspeed MiniMaxOpen weights Awaiting results Source
Mar 18 MiMo-V2-Omni Xiaomi 53.8 Source
Mar 18 MiMo-V2-Pro Xiaomi 54.0 Source
Mar 17 GPT-5.4 mini OpenAI 56.9#76 Source
Mar 17 GPT-5.4 nano OpenAI 57.4#75 Source
Mar 16 Mistral Small 4 Mistral AIOpen weights 48.5 Source
Mar 16 Mistral Small (latest) Mistral AIOpen weights Awaiting results Source
Mar 16 Nemotron VoiceChat NVIDIAOpen weights Awaiting results Source
Mar 16 GLM-5-Turbo Z.ai Awaiting results Source
Mar 11 Nemotron 3 Super 120B A12B NVIDIAOpen weights 53.1 Source
Mar 9 Grok 4.20 (Non-Reasoning) xAI Awaiting results Source
Mar 9 Grok 4.20 (Reasoning) xAI 57.7#73 Source
Mar 5 GPT-5.4 OpenAI 69.7#13 Source
Mar 5 GPT-5.4 Pro OpenAI 61.3#58 Source
Mar 3 Gemini 3.1 Flash Lite Preview Google 42.6 Source
Mar 3 GPT-5.3 Chat (latest) OpenAI 53.3 Source

February 202627 releases

Feb 24 GPT-5.3 Codex OpenAI 56.2 Source
Feb 23 Qwen3.5 122B-A10B Alibaba / QwenOpen weights 56.8 Source
Feb 23 Qwen3.5 27B Alibaba / QwenOpen weights 56.8 Source
Feb 23 Qwen3.5 35B-A3B Alibaba / QwenOpen weights 62.7#49 Source
Feb 23 Qwen3.5 9B Alibaba / QwenOpen weights 55.1 Source
Feb 23 Qwen3.5 Flash Alibaba / Qwen 59.5#63 Source
Feb 19 Gemini 3.1 Pro Preview Google 68.1#22 Source
Feb 19 Gemini 3.1 Pro Preview Custom Tools Google 56.4 Source
Feb 19 Trendyol Asure 12B TrendyolOpen weights Awaiting results Source
Feb 18 Sarvam 30B Sarvam AIOpen weights Awaiting results Source
Feb 17 Claude Sonnet 4.6 Anthropic 68.3#20 Source
Feb 17 Tiny Aya Earth CohereOpen weights Awaiting results Source
Feb 17 Tiny Aya Fire CohereOpen weights Awaiting results Source
Feb 17 Tiny Aya Global CohereOpen weights Awaiting results Source
Feb 17 Tiny Aya Water CohereOpen weights Awaiting results Source
Feb 16 Qwen3.5 Plus Alibaba / Qwen 59.0 Source
Feb 15 Qwen3.5 397B-A17B Alibaba / QwenOpen weights 64.0#39 Source
Feb 14 Seed 2.0 Code ByteDance Seed Awaiting results Source
Feb 14 Seed 2.0 Lite ByteDance Seed Awaiting results Source
Feb 14 Seed 2.0 Mini ByteDance Seed Awaiting results Source
Feb 14 Seed 2.0 Pro ByteDance Seed Awaiting results Source
Feb 13 MiniMax-M2.5-highspeed MiniMaxOpen weights Awaiting results Source
Feb 12 MiniMax-M2.5 MiniMaxOpen weights 57.8#72 Source
Feb 12 GLM-5 Z.aiOpen weights 59.4#65 Source
Feb 5 Claude Opus 4.6 Anthropic 70.8#10 Source
Feb 5 GPT-5.3 Codex Spark OpenAI Awaiting results Source
Feb 3 Qwen3 Coder Next Alibaba / QwenOpen weights Awaiting results Source

January 202611 releases

Jan 29 Step 3.5 Flash StepFunOpen weights 53.0#98 Source
Jan 27 Trinity Large Preview Arcee AIOpen weights 52.5 Source
Jan 27 DeepSeek OCR 2 DeepSeekOpen weights Awaiting results Source
Jan 23 MiniMax-M2 Her MiniMax Awaiting results Source
Jan 22 Nemotron Content Safety Reasoning 4B NVIDIAOpen weights Awaiting results Source
Jan 19 GLM-4.7-Flash Z.aiOpen weights 53.3#97 Source
Jan 19 GLM-4.7-FlashX Z.aiOpen weights Awaiting results Source
Jan 14 GPT-5.2 Codex OpenAI 57.8 Source
Jan 1 Jamba Mini AI21 LabsOpen weights Awaiting results Source
Jan 1 Kimi K2.5 Moonshot AIOpen weights 59.0#66 Source
Jan 1 Solar Pro 3 Upstage Awaiting results Source

December 202526 releases

Dec 28 Seed 1.8 ByteDance Seed Awaiting results Source
Dec 23 MiniMax-M2.1 MiniMaxOpen weights 50.6 Source
Dec 22 GLM-4.7 Z.aiOpen weights 61.3#57 Source
Dec 17 Gemini 3 Flash Preview Google 54.8#91 Source
Dec 16 MiMo-V2-Flash XiaomiOpen weights 53.4 Source
Dec 15 Nemotron 3 Nano 30B A3B NVIDIAOpen weights Awaiting results Source
Dec 11 GPT-5.2 OpenAI 65.9#33 Source
Dec 11 GPT-5.2 Chat OpenAI Awaiting results Source
Dec 11 GPT-5.2 Pro OpenAI 55.8 Source
Dec 9 Devstral 2 Mistral AIOpen weights 48.4 Source
Dec 9 Devstral Small 2 Mistral AIOpen weights Awaiting results Source
Dec 8 GLM-4.6V Z.aiOpen weights 53.1 Source
Dec 8 GLM-4.6V-Flash Z.aiOpen weights Awaiting results Source
Dec 4 GPT-5.1 Codex Max OpenAI Awaiting results Source
Dec 2 Nova 2 Lite Amazon 52.9 Source
Dec 2 Devstral 2 (latest) Mistral AIOpen weights Awaiting results Source
Dec 2 Ministral 14B Mistral AIOpen weights Awaiting results Source
Dec 2 Ministral 3 14B Mistral AIOpen weights Awaiting results Source
Dec 2 Ministral 3 3B Mistral AIOpen weights Awaiting results Source
Dec 2 Ministral 3 8B Mistral AIOpen weights Awaiting results Source
Dec 2 Mistral Large 3 Mistral AIOpen weights 44.7 Source
Dec 1 Trinity Mini Arcee AIOpen weights Awaiting results Source
Dec 1 Trinity Nano Preview Arcee AIOpen weights Awaiting results Source
Dec 1 DeepSeek Chat DeepSeekOpen weights 53.5 Source
Dec 1 DeepSeek Reasoner DeepSeekOpen weights 58.9 Source
Dec 1 DeepSeek V3.2 DeepSeekOpen weights 53.3#96 Source

November 202511 releases

Nov 24 Claude Opus 4.5 (latest) Anthropic 53.1 Source
Nov 19 Grok 4.1 Fast xAI Awaiting results Source
Nov 19 Grok 4.1 Fast (Reasoning) xAI 53.6 Source
Nov 18 Gemini 3 Pro Preview Google 58.6#68 Source
Nov 13 GPT-5.1 OpenAI 55.7#85 Source
Nov 13 GPT-5.1 Chat OpenAI Awaiting results Source
Nov 13 GPT-5.1 Codex OpenAI 51.8 Source
Nov 13 GPT-5.1 Codex mini OpenAI Awaiting results Source
Nov 6 Kimi K2 Thinking Moonshot AIOpen weights 52.1 Source
Nov 6 Kimi K2 Thinking Turbo Moonshot AIOpen weights 66.1#32 Source
Nov 1 Claude Opus 4.5 Anthropic 62.6#50 Source

October 202512 releases

Oct 29 GPT OSS Safeguard 120B OpenAIOpen weights Awaiting results Source
Oct 29 GPT OSS Safeguard 20B OpenAIOpen weights Awaiting results Source
Oct 28 Llama 3.1 Nemotron Safety Guard 8B v3 NVIDIAOpen weights Awaiting results Source
Oct 28 Nemotron Nano 12B v2 VL NVIDIAOpen weights Awaiting results Source
Oct 27 MiniMax-M2 MiniMaxOpen weights 55.7#84 Source
Oct 15 Claude Haiku 4.5 (latest) Anthropic 47.3 Source
Oct 15 Claude Haiku 4.5 Anthropic 60.5#62 Source
Oct 15 Seed 1.6 ByteDance Seed Awaiting results Source
Oct 7 Gemini 2.5 Computer Use Preview Google Awaiting results Source
Oct 6 GPT-5 Pro OpenAI 45.8#117 Source
Oct 2 Granite-4.0-H-Micro IBMOpen weights Awaiting results Source
Oct 2 Granite-4.0-H-Small IBMOpen weights Awaiting results Source

September 202515 releases

Sep 30 GLM-4.6 Z.aiOpen weights 47.8#114 Source
Sep 29 Claude Sonnet 4.5 (latest) Anthropic 48.2 Source
Sep 29 Claude Sonnet 4.5 Anthropic 53.9#94 Source
Sep 23 Gemma-SEA-LION-v4-27B-IT AI SingaporeOpen weights Awaiting results Source
Sep 23 Qwen3 Max Alibaba / Qwen 50.2#108 Source
Sep 23 Qwen3 VL 235B A22B Instruct Alibaba / QwenOpen weights 53.8 Source
Sep 23 Qwen3 VL 235B A22B Thinking Alibaba / QwenOpen weights 53.5 Source
Sep 23 Qwen3-VL Plus Alibaba / Qwen Awaiting results Source
Sep 18 Magistral Small 1.2 Mistral AIOpen weights 47.7 Source
Sep 15 GPT-5-Codex OpenAI 49.5 Source
Sep 2 Apertus 70B Swiss AIOpen weights Awaiting results Source
Sep 2 Apertus 8B Swiss AIOpen weights Awaiting results Source
Sep 1 Sarvam 105B Sarvam AIOpen weights Awaiting results Source
Sep 1 Qwen3-Next 80B-A3B Instruct Alibaba / QwenOpen weights 53.7 Source
Sep 1 Qwen3-Next 80B-A3B (Thinking) Alibaba / QwenOpen weights 53.0 Source

August 202515 releases

Aug 28 Seed 1.6 Flash ByteDance Seed Awaiting results Source
Aug 21 Command A Reasoning CohereOpen weights Awaiting results Source
Aug 21 DeepSeek-V3.1 DeepSeekOpen weights 53.7 Source
Aug 18 Gemini 2.0 Flash Google 40.6 Source
Aug 18 Nemotron Nano 9B v2 NVIDIAOpen weights Awaiting results Source
Aug 15 Seed 1.6 Vision ByteDance Seed Awaiting results Source
Aug 11 GLM-4.5V Z.aiOpen weights 41.6 Source
Aug 7 GPT-5 OpenAI 55.7#83 Source
Aug 7 GPT-5 Chat (latest) OpenAI Awaiting results Source
Aug 7 GPT-5 Mini OpenAI 50.6#105 Source
Aug 7 GPT-5 Nano OpenAI 39.1#129 Source
Aug 5 Claude Opus 4.1 (latest) Anthropic 46.4 Source
Aug 5 Claude Opus 4.1 Anthropic 51.5#102 Source
Aug 5 GPT OSS 120B OpenAIOpen weights 54.8#90 Source
Aug 5 GPT OSS 20B OpenAIOpen weights 52.5#100 Source

July 202514 releases

Jul 31 Command A Vision CohereOpen weights Awaiting results Source
Jul 30 Codestral 25.08 Mistral AI Awaiting results Source
Jul 28 Qwen Flash Alibaba / Qwen Awaiting results Source
Jul 28 Qwen3 Coder Flash Alibaba / Qwen Awaiting results Source
Jul 28 GLM-4.5 Z.aiOpen weights 51.0 Source
Jul 28 GLM-4.5-Air Z.aiOpen weights 45.3 Source
Jul 28 GLM-4.5-Flash Z.ai Awaiting results Source
Jul 25 Llama 3.3 Nemotron Super 49B v1.5 NVIDIAOpen weights 52.5 Source
Jul 23 Qwen3 Coder Plus Alibaba / Qwen Awaiting results Source
Jul 22 Gemini 2.5 Flash-Lite Google 48.0 Source
Jul 21 Qwen3 235B-A22B Instruct 2507 Alibaba / QwenOpen weights 42.4 Source
Jul 10 Devstral Medium Mistral AI 50.5 Source
Jul 10 Devstral Small Mistral AIOpen weights 49.3 Source
Jul 1 Jamba Large AI21 LabsOpen weights Awaiting results Source

June 20256 releases

Jun 20 Mistral Small 3.2 Mistral AIOpen weights 52.5 Source
Jun 17 Gemini 2.5 Flash Google 45.0 Source
Jun 11 Mistral Nemotron NVIDIAOpen weights Awaiting results Source
Jun 10 Magistral Small Mistral AIOpen weights 37.1 Source
Jun 10 o3-pro OpenAI 52.0 Source
Jun 5 Gemini 2.5 Pro Google 45.2#119 Source

May 20256 releases

May 22 Claude Opus 4 (latest) Anthropic Awaiting results Source
May 22 Claude Opus 4 Anthropic 55.5#87 Source
May 22 Claude Sonnet 4 (latest) Anthropic 49.7 Source
May 22 Claude Sonnet 4 Anthropic 46.6#115 Source
May 20 Solar Pro 2 Upstage Awaiting results Source
May 7 Mistral Medium 3 Mistral AI 33.0#136 Source

April 202518 releases

Apr 30 Nova Premier Amazon Awaiting results Source
Apr 28 Qwen3 30B A3B Alibaba / QwenOpen weights 52.6#99 Source
Apr 28 Palmyra X5 Writer Awaiting results Source
Apr 16 o3 OpenAI 55.4#88 Source
Apr 16 o4-mini OpenAI 51.2#103 Source
Apr 15 Llama 3.1 Nemotron 70B Instruct NVIDIAOpen weights 51.5 Source
Apr 14 GPT-4.1 OpenAI 41.5#124 Source
Apr 14 GPT-4.1 mini OpenAI 36.9#132 Source
Apr 14 GPT-4.1 nano OpenAI 32.1#139 Source
Apr 8 Pixtral Large (25.02) Mistral AI Awaiting results Source
Apr 7 Llama 3.1 Nemotron Ultra 253B NVIDIAOpen weights Awaiting results Source
Apr 7 Llama 3.3 Nemotron Super 49B v1 NVIDIAOpen weights Awaiting results Source
Apr 5 Llama 4 Maverick 17B Instruct MetaOpen weights 30.0#141 Source
Apr 5 Llama 4 Scout 17B Instruct MetaOpen weights 51.0#104 Source
Apr 1 Qwen3 235B-A22B Alibaba / QwenOpen weights 50.3#107 Source
Apr 1 Qwen3 32B Alibaba / QwenOpen weights 50.4#106 Source
Apr 1 Qwen3-Coder 30B-A3B Instruct Alibaba / QwenOpen weights 48.0 Source
Apr 1 Qwen3-Coder 480B-A35B Instruct Alibaba / QwenOpen weights 52.7 Source

March 202512 releases

Mar 24 DeepSeek V3 0324 DeepSeekOpen weights 55.7#82 Source
Mar 19 o1-pro OpenAI 44.7 Source
Mar 17 Magistral Medium (latest) Mistral AI 44.1 Source
Mar 17 Mistral Small 3.1 24B Mistral AIOpen weights 48.4#111 Source
Mar 13 Command A CohereOpen weights 52.4 Source
Mar 12 Gemma 3 12B IT GoogleOpen weights 45.1#120 Source
Mar 12 Gemma 3 27B IT GoogleOpen weights 42.0#122 Source
Mar 12 Gemma 3 4B IT GoogleOpen weights 39.2#128 Source
Mar 5 QwQ 32B Alibaba / QwenOpen weights 48.2#112 Source
Mar 5 QwQ Plus Alibaba / Qwen 53.9 Source
Mar 4 Aya Vision 32B CohereOpen weights Awaiting results Source
Mar 4 Aya Vision 8B CohereOpen weights Awaiting results Source

February 20254 releases

Feb 27 Command R7B Arabic CohereOpen weights Awaiting results Source
Feb 25 Gemini 2.0 Flash-Lite Google Awaiting results Source
Feb 19 Claude Sonnet 3.7 Anthropic 48.9#110 Source
Feb 1 Sonar Deep Research Perplexity Awaiting results Source

January 20253 releases

Jan 23 ALLaM-2-7b SDAIAOpen weights Awaiting results Source
Jan 20 DeepSeek-R1 DeepSeekOpen weights 47.9#113 Source
Jan 20 DeepSeek-R1-Distill-Qwen-32B DeepSeekOpen weights 52.9 Source

December 20249 releases

Dec 26 DeepSeek-V3 DeepSeekOpen weights 54.1#93 Source
Dec 20 o3-mini OpenAI 41.6#123 Source
Dec 11 Phi-4-mini MicrosoftOpen weights Awaiting results Source
Dec 6 Llama-3.3-70B-Instruct MetaOpen weights 32.7#137 Source
Dec 5 o1 OpenAI Awaiting results Source
Dec 3 Nova Lite Amazon 36.6#134 Source
Dec 3 Nova Micro Amazon 50.2 Source
Dec 3 Nova Pro Amazon 37.4#131 Source
Dec 2 Command R7B CohereOpen weights Awaiting results Source

November 20247 releases

Nov 20 GPT-4o (2024-11-20) OpenAI 42.2#121 Source
Nov 18 Mistral Large 2.1 Mistral AIOpen weights 35.3#135 Source
Nov 12 Qwen2.5-Coder-0.5B Alibaba / QwenOpen weights Awaiting results Source
Nov 12 Qwen2.5-Coder-32B-Instruct Alibaba / QwenOpen weights 39.6#127 Source
Nov 1 Qwen Turbo Alibaba / Qwen 46.6 Source
Nov 1 Mistral Large (latest) Mistral AIOpen weights Awaiting results Source
Nov 1 Pixtral Large (latest) Mistral AIOpen weights Awaiting results Source

October 20247 releases

Oct 24 Aya Expanse 32B CohereOpen weights 50.4 Source
Oct 24 Aya Expanse 8B CohereOpen weights 49.7 Source
Oct 22 Claude Haiku 3.5 Anthropic 40.8#125 Source
Oct 22 Claude Sonnet 3.5 v2 Anthropic 51.9#101 Source
Oct 16 Ministral 3B Mistral AIOpen weights Awaiting results Source
Oct 16 Ministral 8B Instruct Mistral AIOpen weights Awaiting results Source
Oct 9 Palmyra X4 Writer Awaiting results Source

September 20245 releases

Sep 25 Llama-3.2-11B-Vision-Instruct MetaOpen weights Awaiting results Source
Sep 25 Llama-3.2-1B MetaOpen weights 32.1#138 Source
Sep 25 Llama-3.2-3B MetaOpen weights 48.3 Source
Sep 1 Pixtral 12B Mistral AIOpen weights Awaiting results Source
Sep 1 Qwen2.5-VL 72B Instruct Alibaba / QwenOpen weights Awaiting results Source

August 20244 releases

Aug 30 Command R CohereOpen weights 49.8 Source
Aug 30 Command R+ CohereOpen weights 50.5 Source
Aug 21 Nemotron Mini 4B Instruct NVIDIAOpen weights Awaiting results Source
Aug 6 GPT-4o (2024-08-06) OpenAI 36.7#133 Source

July 20245 releases

Jul 23 Llama-3.1-70B-Instruct MetaOpen weights 45.7#118 Source
Jul 23 Llama-3.1-8B-Instruct MetaOpen weights 37.7#130 Source
Jul 23 Llama-Guard-3-8B MetaOpen weights Awaiting results Source
Jul 18 GPT-4o mini OpenAI 22.9#142 Source
Jul 1 Mistral Nemo Mistral AIOpen weights Awaiting results Source

June 20242 releases

Jun 26 o3-deep-research OpenAI Awaiting results Source
Jun 26 o4-mini-deep-research OpenAI Awaiting results Source

May 20247 releases

May 29 Codestral-22B-v0.1 Mistral AIOpen weights Awaiting results Source
May 29 Codestral (latest) Mistral AIOpen weights Awaiting results Source
May 15 Vision Large Vispark Awaiting results Source
May 15 Vision Medium Vispark Awaiting results Source
May 15 Vision Small Vispark Awaiting results Source
May 13 GPT-4o OpenAI 31.2#140 Source
May 13 GPT-4o (2024-05-13) OpenAI 49.4#109 Source

April 20242 releases

Apr 8 Qwen-VL Max Alibaba / Qwen Awaiting results Source
Apr 3 Qwen Max Alibaba / Qwen 53.0 Source

March 20241 release

Mar 13 Claude Haiku 3 Anthropic 39.9#126 Source

January 20245 releases

Jan 25 Qwen Plus Alibaba / Qwen Awaiting results Source
Jan 25 Qwen-VL Plus Alibaba / Qwen Awaiting results Source
Jan 1 Sonar Perplexity Awaiting results Source
Jan 1 Sonar Pro Perplexity Awaiting results Source
Jan 1 Sonar Reasoning Pro Perplexity Awaiting results Source

November 20233 releases

Nov 6 GPT-3.5-turbo OpenAI Awaiting results Source
Nov 6 GPT-4 OpenAI Awaiting results Source
Nov 6 GPT-4 Turbo OpenAI Awaiting results Source