OutYet.ai
OutYet.ai
The daily briefing
A quiet day in the waiting room
Saturday, November 21, 2026 · what moved in the AI release cycle in those 24 hours.
One click creates your free account (or signs you into an existing one) and turns on alerts for the Daily Briefing. There's no password to set, and you can unsubscribe any time.
New benchmark readings
- Claude Fable 5.2 Coding: 92.3 · BenchLM.ai
- Claude Fable 5.2 Agentic: 92.9 · BenchLM.ai
- Claude Fable 5.2 Reasoning: 93.7 · BenchLM.ai
- Claude Fable 5.2 Knowledge: 92.5 · BenchLM.ai
- Claude Fable 5.2 MultimodalGrounded: 87.1 · BenchLM.ai
- Claude Fable 5.2 Math: 87.1 · BenchLM.ai
- Claude Fable 5.2 Multilingual: 87.8 · BenchLM.ai
- Claude Fable 5.2 InstructionFollowing: 87.6 · BenchLM.ai
- Claude Fable 5.2 GDP.pdf: 51.8 · Epoch AI
- Muse Ember Agentic: 65.8 · BenchLM.ai
- Muse Ember MultimodalGrounded: 62.2 · BenchLM.ai
- Muse Ember InstructionFollowing: 60.4 · BenchLM.ai
- Qwen3.8 Coding: 67.4 · BenchLM.ai
- Qwen3.8 Agentic: 65.7 · BenchLM.ai
- Qwen3.8 Reasoning: 64.7 · BenchLM.ai
- Qwen3.8 Knowledge: 60.5 · BenchLM.ai
- Qwen3.8 MultimodalGrounded: 65.6 · BenchLM.ai
- Qwen3.8 InstructionFollowing: 61.1 · BenchLM.ai
- Qwen3.8 Math: 62.8 · BenchLM.ai
- Qwen4-Max Agentic: 75.7 · BenchLM.ai
- Qwen4-Max Knowledge: 67.9 · BenchLM.ai
- Qwen4-Max Coding: 76 · BenchLM.ai
- Qwen4-Max Reasoning: 75.7 · BenchLM.ai
- Qwen4-Max MultimodalGrounded: 73.4 · BenchLM.ai
- Qwen4-Max InstructionFollowing: 72.8 · BenchLM.ai
- Tencent Hy4 Agentic: 72.7 · BenchLM.ai
- Tencent Hy4 Reasoning: 66.4 · BenchLM.ai
- Tencent Hy4 MultimodalGrounded: 68.2 · BenchLM.ai
- Tencent Hy4 InstructionFollowing: 67.2 · BenchLM.ai
- Amazon Nova Humanity's Last Exam: 4.4 · Epoch AI
- Claude 3.5 Sonnet Humanity's Last Exam: 4.1 · Epoch AI
- Claude 3.7 Sonnet Humanity's Last Exam: 8 · Epoch AI
- Claude Fable 5 Coding: 77.9 · BenchLM.ai
- Claude Fable 5 Agentic: 71.7 · BenchLM.ai
- Claude Fable 5 Knowledge: 76.8 · BenchLM.ai
- Claude Fable 5 Reasoning: 70.8 · BenchLM.ai
- Claude Fable 5 MultimodalGrounded: 70.1 · BenchLM.ai
- Claude Fable 5 Math: 72.1 · BenchLM.ai
- Claude Fable 5 InstructionFollowing: 70.6 · BenchLM.ai
- Claude Fable 5.1 Coding: 81.2 · BenchLM.ai
- Claude Fable 5.1 Agentic: 80.7 · BenchLM.ai
- Claude Fable 5.1 Reasoning: 75 · BenchLM.ai
- Claude Fable 5.1 Knowledge: 77 · BenchLM.ai
- Claude Fable 5.1 Humanity's Last Exam: 46.5 · Epoch AI
- Claude Fable 5.1 GDP.pdf: 49.4 · Epoch AI
- Claude Fable 5.1 MultimodalGrounded: 76.4 · BenchLM.ai
- Claude Fable 5.1 Math: 75.2 · BenchLM.ai
- Claude Fable 5.1 Multilingual: 69.3 · BenchLM.ai
- Claude Fable 5.1 InstructionFollowing: 73.2 · BenchLM.ai
- Claude Haiku 4.5 ExploitBench: 13.7 · Epoch AI
- Claude Haiku 5.5 Coding: 67.9 · BenchLM.ai
- Claude Haiku 5.5 Agentic: 68.9 · BenchLM.ai
- Claude Haiku 5.5 Reasoning: 62.6 · BenchLM.ai
- Claude Haiku 5.5 Humanity's Last Exam: 30.1 · Epoch AI
- Claude Haiku 5.5 MultimodalGrounded: 63.9 · BenchLM.ai
- Claude Haiku 5.5 Math: 62.3 · BenchLM.ai
- Claude Haiku 5.5 Multilingual: 56.2 · BenchLM.ai
- Claude Haiku 5.5 InstructionFollowing: 58.4 · BenchLM.ai
- Claude Mythos 5 ExploitBench: 70.6 · Epoch AI
- Claude Opus 4 Humanity's Last Exam: 10.7 · Epoch AI
- Claude Opus 4.1 Humanity's Last Exam: 11.5 · Epoch AI
- Claude Opus 4.5 Multilingual: 57.4 · BenchLM.ai
- Claude Opus 4.5 Humanity's Last Exam: 25.2 · Epoch AI
- Claude Opus 4.6 Humanity's Last Exam: 34.4 · Epoch AI
- Claude Opus 4.6 Coding: 60.9 · BenchLM.ai
- Claude Opus 4.6 Knowledge: 59.2 · BenchLM.ai
- Claude Opus 4.6 Math: 57.8 · BenchLM.ai
- Claude Opus 4.6 InstructionFollowing: 56.9 · BenchLM.ai
- Claude Opus 4.7 Coding: 65.2 · BenchLM.ai
- Claude Opus 4.7 Agentic: 62.2 · BenchLM.ai
- Claude Opus 4.7 Knowledge: 59.4 · BenchLM.ai
- Claude Opus 4.7 Humanity's Last Exam: 36.2 · Epoch AI
- Claude Opus 4.7 ExploitBench: 26.5 · Epoch AI
- Claude Opus 4.7 Reasoning: 61 · BenchLM.ai
- Claude Opus 4.7 Math: 61.4 · BenchLM.ai
- Claude Opus 4.7 InstructionFollowing: 61.6 · BenchLM.ai
- Claude Opus 4.8 Coding: 69.6 · BenchLM.ai
- Claude Opus 4.8 Agentic: 66.1 · BenchLM.ai
- Claude Opus 4.8 Knowledge: 60.3 · BenchLM.ai
- Claude Opus 4.8 MultimodalGrounded: 60.8 · BenchLM.ai
- Claude Opus 4.8 Math: 65.4 · BenchLM.ai
- Claude Opus 4.8 Reasoning: 66.1 · BenchLM.ai
- Claude Opus 4.8 Multilingual: 64.5 · BenchLM.ai
- Claude Opus 4.8 InstructionFollowing: 64 · BenchLM.ai
- Claude Opus 5 Coding: 77 · BenchLM.ai
- Claude Opus 5 Agentic: 75.4 · BenchLM.ai
- Claude Opus 5 Knowledge: 70.3 · BenchLM.ai
- Claude Opus 5 MultimodalGrounded: 71.6 · BenchLM.ai
- Claude Opus 5 Reasoning: 74.7 · BenchLM.ai
- Claude Opus 5 Math: 72 · BenchLM.ai
- Claude Opus 5 Multilingual: 69.1 · BenchLM.ai
- Claude Opus 5 InstructionFollowing: 72.3 · BenchLM.ai
- Claude Opus 5.5 Coding: 88.3 · BenchLM.ai
- Claude Opus 5.5 Agentic: 87.3 · BenchLM.ai
- Claude Opus 5.5 Reasoning: 80.8 · BenchLM.ai
- Claude Opus 5.5 Knowledge: 71.6 · BenchLM.ai
- Claude Opus 5.5 MultimodalGrounded: 80.6 · BenchLM.ai
- Claude Opus 5.5 GDP.pdf: 48.8 · Epoch AI
- Claude Opus 5.5 Math: 77.3 · BenchLM.ai
- Claude Opus 5.5 Multilingual: 74.5 · BenchLM.ai
- Claude Opus 5.5 InstructionFollowing: 76.1 · BenchLM.ai
- Claude Sonnet 4 Humanity's Last Exam: 7.8 · Epoch AI
- Claude Sonnet 4.5 Humanity's Last Exam: 13.7 · Epoch AI
- Claude Sonnet 4.6 ExploitBench: 23.6 · Epoch AI
- Claude Sonnet 5 Coding: 62.5 · BenchLM.ai
- Claude Sonnet 5 Agentic: 62.8 · BenchLM.ai
- Claude Sonnet 5 MultimodalGrounded: 60.6 · BenchLM.ai
- Claude Sonnet 5 Reasoning: 62.5 · BenchLM.ai
- Claude Sonnet 5 Math: 59.3 · BenchLM.ai
- Claude Sonnet 5 Multilingual: 59 · BenchLM.ai
- Claude Sonnet 5 InstructionFollowing: 58.4 · BenchLM.ai
- DeepSeek V4 Flash SWE-Bench Pro: 52.6 · Hugging Faceself reported
- DeepSeek V4 Pro SWE-Bench Pro: 55.4 · Hugging Faceself reported
- DeepSeek V4 Pro Reasoning: 64.6 · BenchLM.ai
- DeepSeek V4 Pro Knowledge: 59.8 · BenchLM.ai
- DeepSeek V4 Pro Math: 59.4 · BenchLM.ai
- DeepSeek V4 Pro InstructionFollowing: 56.5 · BenchLM.ai
- DeepSeek V4 Pro Multilingual: 57.5 · BenchLM.ai
- Gemini 1.5 Pro Humanity's Last Exam: 4.6 · Epoch AI
- Gemini 2.0 Flash Humanity's Last Exam: 6.6 · Epoch AI
- Gemini 2.5 Flash Humanity's Last Exam: 12.1 · Epoch AI
- Gemini 2.5 Pro Humanity's Last Exam: 21.6 · Epoch AI
- Gemini 3 Pro Knowledge: 70.2 · BenchLM.ai
- Gemini 3 Pro Humanity's Last Exam: 37.5 · Epoch AI
- Gemini 3 Pro Multilingual: 57.4 · BenchLM.ai
- Gemini 3 Pro Math: 56.7 · BenchLM.ai
- Gemini 3.1 Pro Knowledge: 68.9 · BenchLM.ai
- Gemini 3.1 Pro MultimodalGrounded: 62.3 · BenchLM.ai
- Gemini 3.1 Pro Humanity's Last Exam: 46.4 · Epoch AI
- Gemini 3.1 Pro ExploitBench: 26.1 · Epoch AI
- Gemini 3.1 Pro InstructionFollowing: 55.9 · BenchLM.ai
- Gemini 3.1 Pro Reasoning: 62.8 · BenchLM.ai
- Gemini 3.1 Pro Math: 58.3 · BenchLM.ai
- Gemini 3.5 Flash MultimodalGrounded: 62.9 · BenchLM.ai
- Gemini 3.5 Flash Knowledge: 64.8 · BenchLM.ai
- Gemini 3.5 Flash Reasoning: 60.5 · BenchLM.ai
- Gemini 3.5 Flash Math: 57.9 · BenchLM.ai
- Gemini 3.5 Flash Multilingual: 56.8 · BenchLM.ai
- Gemini 3.6 Flash Knowledge: 65.7 · BenchLM.ai
- Gemini 3.6 Flash MultimodalGrounded: 65.4 · BenchLM.ai
- Gemini 3.6 Flash Reasoning: 60.8 · BenchLM.ai
- Gemini 3.6 Flash Math: 58.1 · BenchLM.ai
- Gemini 3.6 Flash Multilingual: 59.8 · BenchLM.ai
- Gemini 3.6 Flash InstructionFollowing: 57.5 · BenchLM.ai
- Gemini 3.7 Flash Coding: 65.1 · BenchLM.ai
- Gemini 3.7 Flash Agentic: 63.1 · BenchLM.ai
- Gemini 3.7 Flash Knowledge: 69.5 · BenchLM.ai
- Gemini 3.7 Flash MultimodalGrounded: 66.2 · BenchLM.ai
- Gemini 3.7 Flash Reasoning: 66.9 · BenchLM.ai
- Gemini 3.7 Flash Math: 64 · BenchLM.ai
- Gemini 3.7 Flash Multilingual: 64.5 · BenchLM.ai
- Gemini 3.7 Flash InstructionFollowing: 62.2 · BenchLM.ai
- Gemini 3.8 Flash Coding: 65.4 · BenchLM.ai
- Gemini 3.8 Flash Agentic: 65.4 · BenchLM.ai
- Gemini 3.8 Flash Reasoning: 69.2 · BenchLM.ai
- Gemini 3.8 Flash Knowledge: 71.4 · BenchLM.ai
- Gemini 3.8 Flash MultimodalGrounded: 66.8 · BenchLM.ai
- Gemini 3.8 Flash Humanity's Last Exam: 44.5 · Epoch AI
- Gemini 3.8 Flash GDP.pdf: 44.2 · Epoch AI
- Gemini 3.8 Flash Math: 64.2 · BenchLM.ai
- Gemini 3.8 Flash Multilingual: 65.9 · BenchLM.ai
- Gemini 3.8 Flash InstructionFollowing: 65.5 · BenchLM.ai
- Gemini 4 Argon Coding: 78.8 · BenchLM.ai
- Gemini 4 Argon Agentic: 81.7 · BenchLM.ai
- Gemini 4 Argon Knowledge: 78.6 · BenchLM.ai
- Gemini 4 Argon Reasoning: 77.2 · BenchLM.ai
- Gemini 4 Argon GDP.pdf: 53.6 · Epoch AI
- Gemini 4 Argon Math: 74.5 · BenchLM.ai
- Gemini 4 Argon MultimodalGrounded: 73.2 · BenchLM.ai
- Gemini 4 Argon Multilingual: 72.2 · BenchLM.ai
- Gemini 4 Argon InstructionFollowing: 74.3 · BenchLM.ai
- Gemini 4 Carbon Coding: 91.7 · BenchLM.ai
- Gemini 4 Carbon Reasoning: 87.5 · BenchLM.ai
- Gemini 4 Carbon Agentic: 88.5 · BenchLM.ai
- Gemini 4 Carbon Knowledge: 83.2 · BenchLM.ai
- Gemini 4 Carbon Math: 80.1 · BenchLM.ai
- Gemini 4 Carbon MultimodalGrounded: 85.8 · BenchLM.ai
- Gemini 4 Carbon InstructionFollowing: 82.4 · BenchLM.ai
- Gemini 4 Hydrogen Coding: 77.8 · BenchLM.ai
- Gemini 4 Hydrogen Agentic: 81.5 · BenchLM.ai
- Gemini 4 Hydrogen Reasoning: 76.9 · BenchLM.ai
- Gemini 4 Hydrogen Knowledge: 78.3 · BenchLM.ai
- Gemini 4 Hydrogen Math: 74.2 · BenchLM.ai
- Gemini 4 Hydrogen MultimodalGrounded: 72.9 · BenchLM.ai
- Gemini 4 Hydrogen InstructionFollowing: 74 · BenchLM.ai
- Gemini 4 Neon Agentic: 92.1 · BenchLM.ai
- Gemini 4 Neon Reasoning: 88.9 · BenchLM.ai
- Gemini 4 Neon Coding: 93 · BenchLM.ai
- Gemini 4 Neon Knowledge: 87.8 · BenchLM.ai
- Gemini 4 Neon Math: 83.8 · BenchLM.ai
- Gemini 4 Neon MultimodalGrounded: 80.8 · BenchLM.ai
- Gemini 4 Neon InstructionFollowing: 86.9 · BenchLM.ai
- Glm 5 2 Coding: 61 · BenchLM.ai
- Glm 5 2 InstructionFollowing: 55.1 · BenchLM.ai
- Glm 5 2 Math: 57.3 · BenchLM.ai
- GLM-4.5 Humanity's Last Exam: 8.3 · Epoch AI
- GLM-4.6 SWE-Bench Pro: 9.7 · Hugging Faceself reported
- GLM-5 Multilingual: 53.1 · BenchLM.ai
- GLM-5.1 ExploitBench: 16 · Epoch AI
- GLM-5.1 SWE-Bench Pro: 58.4 · Hugging Faceself reported
- GLM-5.2 SWE-Bench Pro: 62.1 · Hugging Faceself reported
- GPT-4.1 Humanity's Last Exam: 5.4 · Epoch AI
- GPT-4.5 Humanity's Last Exam: 5.4 · Epoch AI
- GPT-4o Humanity's Last Exam: 2.7 · Epoch AI
- GPT-5 Humanity's Last Exam: 31.6 · Epoch AI
- GPT-5 Multilingual: 52.2 · BenchLM.ai
- GPT-5.1 Humanity's Last Exam: 23.7 · Epoch AI
- GPT-5.2 Humanity's Last Exam: 27.8 · Epoch AI
- GPT-5.2 Reasoning: 70.2 · BenchLM.ai
- GPT-5.2 Knowledge: 60.7 · BenchLM.ai
- GPT-5.2 Math: 59.5 · BenchLM.ai
- GPT-5.4 Humanity's Last Exam: 36.2 · Epoch AI
- GPT-5.5 Agentic: 68.2 · BenchLM.ai
- GPT-5.5 MultimodalGrounded: 66.9 · BenchLM.ai
- GPT-5.5 Coding: 64.8 · BenchLM.ai
- GPT-5.5 Knowledge: 68.6 · BenchLM.ai
- GPT-5.5 InstructionFollowing: 65.8 · BenchLM.ai
- GPT-5.5 ExploitBench: 41.8 · Epoch AI
- GPT-5.5 Reasoning: 74.9 · BenchLM.ai
- GPT-5.5 Math: 71.2 · BenchLM.ai
- GPT-5.6 Luna Coding: 61 · BenchLM.ai
- GPT-5.6 Luna Agentic: 62 · BenchLM.ai
- GPT-5.6 Luna MultimodalGrounded: 62.8 · BenchLM.ai
- GPT-5.6 Luna Math: 58 · BenchLM.ai
- GPT-5.6 Luna Multilingual: 51.7 · BenchLM.ai
- GPT-5.6 Sol Coding: 74.1 · BenchLM.ai
- GPT-5.6 Sol Agentic: 72.4 · BenchLM.ai
- GPT-5.6 Sol Knowledge: 71.7 · BenchLM.ai
- GPT-5.6 Sol MultimodalGrounded: 71.6 · BenchLM.ai
- GPT-5.6 Sol InstructionFollowing: 66.9 · BenchLM.ai
- GPT-5.6 Sol Reasoning: 72.8 · BenchLM.ai
- GPT-5.6 Sol Math: 71.8 · BenchLM.ai
- GPT-5.6 Sol Multilingual: 67.8 · BenchLM.ai
- GPT-5.6 Terra Coding: 68.5 · BenchLM.ai
- GPT-5.6 Terra Agentic: 66.1 · BenchLM.ai
- GPT-5.6 Terra Knowledge: 62.2 · BenchLM.ai
- GPT-5.6 Terra MultimodalGrounded: 66.2 · BenchLM.ai
- GPT-5.6 Terra InstructionFollowing: 61.1 · BenchLM.ai
- GPT-5.6 Terra Reasoning: 63.3 · BenchLM.ai
- GPT-5.6 Terra Math: 65.5 · BenchLM.ai
- GPT-5.6 Terra Multilingual: 61.9 · BenchLM.ai
- GPT-6 Astra Coding: 82 · BenchLM.ai
- GPT-6 Astra Agentic: 86.3 · BenchLM.ai
- GPT-6 Astra Reasoning: 86.9 · BenchLM.ai
- GPT-6 Astra Knowledge: 79.7 · BenchLM.ai
- GPT-6 Astra Humanity's Last Exam: 54.8 · Epoch AI
- GPT-6 Astra MultimodalGrounded: 79.2 · BenchLM.ai
- GPT-6 Astra Math: 79.3 · BenchLM.ai
- GPT-6 Astra Multilingual: 73.9 · BenchLM.ai
- GPT-6 Astra InstructionFollowing: 78.3 · BenchLM.ai
- GPT-6 Luna Coding: 61.2 · BenchLM.ai
- GPT-6 Luna Agentic: 63.8 · BenchLM.ai
- GPT-6 Luna Knowledge: 62.7 · BenchLM.ai
- GPT-6 Luna MultimodalGrounded: 65.2 · BenchLM.ai
- GPT-6 Luna Math: 61.6 · BenchLM.ai
- GPT-6 Luna Multilingual: 58.5 · BenchLM.ai
- GPT-6 Luna InstructionFollowing: 57.2 · BenchLM.ai
- GPT-6 Sol Coding: 74.3 · BenchLM.ai
- GPT-6 Sol Agentic: 75.3 · BenchLM.ai
- GPT-6 Sol Reasoning: 73.1 · BenchLM.ai
- GPT-6 Sol Knowledge: 71.9 · BenchLM.ai
- GPT-6 Sol MultimodalGrounded: 72.8 · BenchLM.ai
- GPT-6 Sol Math: 73.1 · BenchLM.ai
- GPT-6 Sol Multilingual: 68.1 · BenchLM.ai
- GPT-6 Sol InstructionFollowing: 67.9 · BenchLM.ai
- GPT-6.1 Sol Coding: 80.3 · BenchLM.ai
- GPT-6.1 Sol Agentic: 83.2 · BenchLM.ai
- GPT-6.1 Sol Reasoning: 81 · BenchLM.ai
- GPT-6.1 Sol Knowledge: 78.4 · BenchLM.ai
- GPT-6.1 Sol MultimodalGrounded: 77.5 · BenchLM.ai
- GPT-6.1 Sol Math: 77.9 · BenchLM.ai
- GPT-6.1 Sol Multilingual: 71.3 · BenchLM.ai
- GPT-6.1 Sol InstructionFollowing: 73.3 · BenchLM.ai
- GPT-6.1 Terra Agentic: 82.2 · BenchLM.ai
- GPT-6.1 Terra Knowledge: 75.5 · BenchLM.ai
- GPT-6.1 Terra MultimodalGrounded: 74.4 · BenchLM.ai
- GPT-6.1 Terra Reasoning: 80.7 · BenchLM.ai
- GPT-6.1 Terra Coding: 80 · BenchLM.ai
- GPT-6.1 Terra Math: 76.1 · BenchLM.ai
- GPT-6.1 Terra InstructionFollowing: 73 · BenchLM.ai
- GPT-6.2 Astra Agentic: 93 · BenchLM.ai
- GPT-6.2 Astra Knowledge: 88.6 · BenchLM.ai
- GPT-6.2 Astra Coding: 91.8 · BenchLM.ai
- GPT-6.2 Astra Reasoning: 87.1 · BenchLM.ai
- GPT-6.2 Astra Math: 83.2 · BenchLM.ai
- GPT-6.2 Astra InstructionFollowing: 83 · BenchLM.ai
- GPT-6.2 Astra MultimodalGrounded: 90.3 · BenchLM.ai
- GPT-6.2 Sol Agentic: 83.6 · BenchLM.ai
- GPT-6.2 Sol Knowledge: 80.8 · BenchLM.ai
- GPT-6.2 Sol Coding: 83.3 · BenchLM.ai
- GPT-6.2 Sol Reasoning: 81.2 · BenchLM.ai
- GPT-6.2 Sol InstructionFollowing: 73.5 · BenchLM.ai
- GPT-6.2 Sol MultimodalGrounded: 83.9 · BenchLM.ai
- gpt-oss SWE-Bench Pro: 16.2 · Hugging Faceself reported
- Grok 4.5 Knowledge: 61.3 · BenchLM.ai
- Grok 4.5 Reasoning: 59.9 · BenchLM.ai
- Grok 4.5 Math: 57.6 · BenchLM.ai
- Grok 4.5 MultimodalGrounded: 62.8 · BenchLM.ai
- Grok 4.5 Multilingual: 58.9 · BenchLM.ai
- Grok 4.5 InstructionFollowing: 57.8 · BenchLM.ai
- Grok 4.6 Coding: 67.2 · BenchLM.ai
- Grok 4.6 Agentic: 65.4 · BenchLM.ai
- Grok 4.6 Knowledge: 62.7 · BenchLM.ai
- Grok 4.6 Reasoning: 63 · BenchLM.ai
- Grok 4.6 Math: 62.5 · BenchLM.ai
- Grok 4.6 MultimodalGrounded: 68.7 · BenchLM.ai
- Grok 4.6 InstructionFollowing: 61.6 · BenchLM.ai
- Kimi K2 SWE-Bench Pro: 27.7 · Hugging Faceself reported
- Kimi K2.5 Multilingual: 52.2 · BenchLM.ai
- Kimi K2.5 Humanity's Last Exam: 24.4 · Epoch AI
- Kimi K2.5 SWE-Bench Pro: 50.7 · Hugging Faceself reported
- Kimi K2.6 ExploitBench: 16.3 · Epoch AI
- Kimi K2.6 SWE-Bench Pro: 58.6 · Hugging Faceself reported
- Kimi K2.6 Math: 53.5 · BenchLM.ai
- Kimi K2.6 Multilingual: 57.2 · BenchLM.ai
- Kimi K3 MultimodalGrounded: 65.2 · BenchLM.ai
- Kimi K3 Coding: 65.4 · BenchLM.ai
- Kimi K3 Agentic: 65.7 · BenchLM.ai
- Kimi K3 Knowledge: 66.3 · BenchLM.ai
- Kimi K3 Reasoning: 62 · BenchLM.ai
- Kimi K3 Math: 59.3 · BenchLM.ai
- Kimi K3 InstructionFollowing: 64 · BenchLM.ai
- Llama 4 Humanity's Last Exam: 5.7 · Epoch AI
- MiniMax M2.1 SWE-Bench Pro: 36.8 · Hugging Faceself reported
- MiniMax M2.5 SWE-Bench Pro: 55.4 · Hugging Faceself reported
- MiniMax M2.7 ExploitBench: 13.3 · Epoch AI
- MiniMax M2.7 SWE-Bench Pro: 56.2 · Hugging Faceself reported
- MiniMax M2.7 Multilingual: 55.1 · BenchLM.ai
- MiniMax M3 SWE-Bench Pro: 59 · Hugging Faceself reported
- Mistral Large 4 Coding: 63.2 · BenchLM.ai
- Mistral Large 4 Math: 55.5 · BenchLM.ai
- Mistral Medium 3 Humanity's Last Exam: 4.5 · Epoch AI
- Muse Glimmer 30B SWE-Bench Pro: 51.2 · Hugging Faceself reported
- Muse Spark Humanity's Last Exam: 40.6 · Epoch AI
- Nemotron 3 Multilingual: 48.8 · BenchLM.ai
- North Mini Code SWE-Bench Pro: 40.2 · Hugging Faceself reported
- o1 Humanity's Last Exam: 8.1 · Epoch AI
- o3 Humanity's Last Exam: 20.3 · Epoch AI
- o3 Multilingual: 50.6 · BenchLM.ai
- o4-mini Humanity's Last Exam: 18.1 · Epoch AI
- Qwen 3 SWE-Bench Pro: 21.4 · Hugging Faceself reported
- Qwen 3.5 Multilingual: 50.9 · BenchLM.ai
- Qwen 3.6 Multilingual: 54.7 · BenchLM.ai
- Qwen 3.6 SWE-Bench Pro: 53.5 · Hugging Faceself reported
- Qwen 3.7 Max Knowledge: 59.4 · BenchLM.ai
- Qwen 3.7 Max Multilingual: 59.3 · BenchLM.ai
- Qwen 3.7 Max Math: 57.4 · BenchLM.ai
- Qwen 3.7 Max Reasoning: 58 · BenchLM.ai
- Qwen3-Coder SWE-Bench Pro: 38.7 · Hugging Faceself reported
- Qwen3-Coder-Next SWE-Bench Pro: 44.3 · Hugging Faceself reported