BenchLeader

Changelog

What changed on BenchLeader each day: models ranked for the first time, new models, new results from 28 independent sources, moves in the BenchLeader Index, and price changes.

Updated every six hours; data as of 16 Nov 2026. Speed and rating drift are in each day's digest.

Get new models and rankings by email

The last 14 days, from 3 Nov 2026. Every earlier day, back to 8 Sep 2026, is in the daily digests.

Show
    1. Prices changed for 3 models

      • Qwen3.5-9Bthinkingcache read $0.063 → $0.137/M (+117%)
      • Qwen3.5-9Bno reasoningcache read $0.063 → $0.137/M (+117%)
      • Qwen3.5-9Bcache read $0.063 → $0.137/M (+117%)
    1. Weekly review

      Claude Fable 5.2 + 8 new AI models: 9 Nov–15 Nov

      9 new models incl. Claude Fable 5.2, Gemini 4 Hydrogen and Muse Ember, Gemma 4 31B up 4.4, 19 price cuts, 1414 new benchmark results: what moved on the BenchLeader Index this week.

    2. Ranked in the BenchLeader Index

      Gemini 4 Hydrogenxhigh

      BenchLeader Index 61.8

    3. Ranked in the BenchLeader Index

      GPT-5.3 Chat

      BenchLeader Index 58.3

    4. Ranked in the BenchLeader Index

      Deepseek v2.5

      BenchLeader Index 45.8

    5. New model listed

      Nemotron 3.5 Bolt E4Bthinking

    6. Vals AI published 317 new results

    7. LiveBench published 200 new results

    8. Aider polyglot leaderboard published 25 new results

    9. DuelLab GameBench 2 published 10 new results

    10. 6 more sources published results · all in the digest

    11. BenchLeader Index order changed

    12. Prices changed for 38 models

    1. Ranked in the BenchLeader Index

      Mistral Large 4medium

      BenchLeader Index 45.9

    2. New model listed

      Particle-1

      Listed at $0.17/M blended

    3. Artificial Analysis published 496 new results

    4. Epoch AI Benchmarking Hub published 3 new results

    5. Design Arena published 2 new results

    6. BenchLeader Index order changed

    7. Prices changed for 16 models

    1. Ranked in the BenchLeader Index

      Gemini 4 Hydrogenhigh

      BenchLeader Index 63.4

    2. Ranked in the BenchLeader Index

      Gemini 4 Carbon

      BenchLeader Index 63.0

    3. Ranked in the BenchLeader Index

      Gemini 4 Argonmedium

      BenchLeader Index 61.6

    4. Ranked in the BenchLeader Index

      Muse Emberxhigh

      BenchLeader Index 49.1

    5. Ranked in the BenchLeader Index

      K-EXAONE 2.0

      BenchLeader Index 42.4

    6. Artificial Analysis published 36 new results

    7. Epoch AI Benchmarking Hub published 19 new results

    8. Arena (LMArena) published 9 new results

    9. Scale AI SEAL published 4 new results

    10. 1 more source published results · all in the digest

    11. Prices changed for 5 models

    1. New model listed

      Gemini 4 Hydrogen

    2. MathArena published 22 new results

    3. Artificial Analysis published 11 new results

    4. Kaggle Benchmarks published 10 new results

    5. Epoch AI Benchmarking Hub published 9 new results

    6. 4 more sources published results · all in the digest

    7. BenchLeader Index order changed

    8. Prices changed for 17 models

    1. Ranked in the BenchLeader Index

      Claude Fable 5.2

      BenchLeader Index 67.8

    2. Ranked in the BenchLeader Index

      Gemini 4 Carbonlow

      BenchLeader Index 60.2

    3. New model listed

      U2 Flash

    4. New model listed

      ERNIE-Light-DT-1.0

      Listed at $1.83/M blended

    5. Epoch AI Benchmarking Hub published 108 new results

    6. ARC Prize published 9 new results

    7. Artificial Analysis published 8 new results

    8. LiveBench published 8 new results

    9. 5 more sources published results · all in the digest

    10. BenchLeader Index order changed

    11. Prices changed for 5 models

    1. Ranked in the BenchLeader Index

      Kimi K3.1 Promax

      BenchLeader Index 60.4

    2. Ranked in the BenchLeader Index

      Muse Embermax

      BenchLeader Index 52.3

    3. Ranked in the BenchLeader Index

      Apodex 1.1

      BenchLeader Index 48.3

    4. New model listed

      Claude Mythos 5.2

      Listed at $16.00/M blended

    5. Epoch AI Benchmarking Hub published 29 new results

    6. Artificial Analysis published 13 new results

    7. Arena (LMArena) published 8 new results

    8. Vals AI published 2 new results

    9. 2 more sources published results · all in the digest

    10. BenchLeader Index order changed

    11. Prices changed for 9 models

    1. Ranked in the BenchLeader Index

      Claude Fable 5.2max

      BenchLeader Index 69.4

    2. Ranked in the BenchLeader Index

      Claude Fable 5.2high

      BenchLeader Index 68.9

    3. Ranked in the BenchLeader Index

      Claude Fable 5.2xhigh

      BenchLeader Index 68.7

    4. Ranked in the BenchLeader Index

      Claude Fable 5.2medium

      BenchLeader Index 66.3

    5. Ranked in the BenchLeader Index

      Claude Fable 5.2low

      BenchLeader Index 65.3

    6. Ranked in the BenchLeader Index

      Agnes 2.5 Pro Theta

      BenchLeader Index 50.8

    7. New model listed

      Agnes 2.5 Pro Theta

    8. New model listed

      Claude Fable 5.2

    9. New model listed

      Muse Ember

      Listed at $0.20/M blended

    10. Arena (LMArena) published 8 new results

    11. Artificial Analysis published a new result

    12. BenchLeader Index order changed

    13. Prices changed for one model

    1. Weekly review

      Kimi K3.1 Pro Together + 11 new AI models: 2 Nov–8 Nov

      12 new models incl. Kimi K3.1 Pro Together, Inkling 2 Small and LFM2.5-24B-A2B, DeepSeek V3.1 up 3.5, 20 price cuts, 314 new benchmark results: what moved on the BenchLeader Index this week.

    2. Ranked in the BenchLeader Index

      DeepSeek V3.2no reasoning

      BenchLeader Index 50.6

    3. New model listed

      LFM2.5-24B-A2B

      Listed at $0.21/M blended

    4. New model listed

      LFM3-1.7B

      Listed at $0.11/M blended

    5. Arena (LMArena) published 45 new results

    6. Vals AI published 39 new results

    7. Epoch AI Benchmarking Hub published 20 new results

    8. Artificial Analysis published 15 new results

    9. 4 more sources published results · all in the digest

    10. BenchLeader Index order changed

    11. Prices changed for 9 models

    1. Prices changed for 4 models

      • MiMo-V2.5input $0.13 → $0.18/M (+38%)
      • MiMo-V2.5no reasoninginput $0.13 → $0.18/M (+38%)
      • MiMo-V2.5output $0.27 → $0.36/M (+33%)
      • MiMo-V2.5no reasoningoutput $0.27 → $0.36/M (+33%)
    1. Ranked in the BenchLeader Index

      Kimi K3.1 Pro Togethermax

      BenchLeader Index 60.5

    2. Ranked in the BenchLeader Index

      Inkling 2 Small

      BenchLeader Index 57.5

    3. New model listed

      Kimi K3.1 Pro Togethermax

    4. New model listed

      Inkling 2 Small

    5. Artificial Analysis published 13 new results

    6. Kaggle Benchmarks published 2 new results

    7. Scale AI SEAL published 2 new results

    8. BenchLeader Index order changed

    9. Prices changed for 7 models

    1. Ranked in the BenchLeader Index

      Muse Wonderhigh

      BenchLeader Index 56.9

    2. New model listed

      Crouton Alpha

    3. New model listed

      Gemini Omni 1.1 Flash

      Listed at $3.38/M blended

    4. New model listed

      Gemini Omni 1.2 Flash

      Listed at $3.38/M blended

    5. New model listed

      Ripple-65B Preview

      Listed at $0.30/M blended

    6. Artificial Analysis published 63 new results

    7. Scale AI SEAL published 8 new results

    8. Epoch AI Benchmarking Hub published 6 new results

    9. Kaggle Benchmarks published 5 new results

    10. Prices changed for one model

    1. Artificial Analysis published 30 new results

    2. DuelLab GameBench 2 published 7 new results

    3. Epoch AI Benchmarking Hub published 3 new results

    4. Vals AI published a new result

    5. BenchLeader Index order changed

    6. Prices changed for 171 models

    1. Ranked in the BenchLeader Index

      Mistral Large 4.0 OSShigh

      BenchLeader Index 50.0

    2. New model listed

      Mistral Large 4.0 OSShigh

    3. ARC Prize published a new result

    4. Kaggle Benchmarks published a new result

    5. Artificial Analysis published a new result

    6. Arena (LMArena) published a new result

    7. Prices changed for 81 models