RLTasksby ulam.ai
Models / Kimi

Kimi / MODEL EVIDENCE

Kimi K2.7 Code

28 benchmarks · 28 observations · 28 sources · released 2026-06-12

Scores at a glance

28 benchmarks · large dot: Kimi K2.7 Code; small dots: closest models where reported

ErdősBench ↗2.620 / 4
2.113.25

Kimi K2.7 Code · ErdősBench · mean progress / 4 · API ↗

GPQA Diamond ↗87.88%
9.2896.4

Kimi K2.7 Code · GPQA diamond · Best score (across scorers) · % ↗

GBAEval ↗0.85%
0.850.85

Kimi K2.7 Code · GBAEval · Overall score · % ↗

ALE-Bench ↗886.23 Performance points
137.782951.32

kimi-k2.7-code · Average contest performance ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

8.9 percentile-point gap

9 of 14 shared benchmark comparisons

9.9 percentile-point gap

9 of 14 shared benchmark comparisons

How similarity is measured

Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.

Filter comparisons to this model →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

  1. Arena leaderboard — WebDev evaluation ↗

    Arena

  2. SciCode Benchmark | Artificial Analysis ↗

    Artificial Analysis

  3. Terminal-Bench Hard Benchmark | Artificial Analysis ↗

    Artificial Analysis

  4. FrontierCode Leaderboard ↗

    Cognition

  5. DeepSWE ↗

    Datacurve

  6. Ale Bench — methodology and published results ↗

    Epoch AI · 2026

  7. APEX-Agents ↗

    Epoch AI

  8. Chess Puzzles ↗

    Epoch AI

  9. CritPt v1 ↗

    Epoch AI

  10. FrontierMath Tier 4 (v2) ↗

    Epoch AI

  11. FrontierMath Tiers 1-3 (v2) ↗

    Epoch AI

  12. GPQA Diamond ↗

    Epoch AI

  13. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  14. SimpleQA Verified ↗

    Epoch AI

  15. Vending Bench 2 — methodology and published results ↗

    Epoch AI · 2026

  16. AI benchmarks & capabilities ↗

    Epoch AI

  17. Kimi K2.7 Code — GBA Eval ↗

    GBA Eval

  18. WeirdML ↗

    Håvard Tveit Ihle

  19. DrugDiscoveryBench — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  20. AI Model Benchmarks — LM Council ↗

    LM Council

  21. ErdősBench: research mathematics, scoped progress and proof audits ↗

    Ulam AI · 2026

  22. Code Migration v1 — evaluation methodology and results ↗

    Vals AI · 2026

  23. LiveCodeBench — evaluation methodology and results ↗

    Vals AI · 2026

  24. ProgramBench — evaluation methodology and results ↗

    Vals AI · 2026

  25. SkillsBench — evaluation methodology and results ↗

    Vals AI · 2026

  26. SWE-bench Verified — evaluation methodology and results ↗

    Vals AI · 2026

  27. Vibe Code Bench — evaluation methodology and results ↗

    Vals AI · 2026

  28. Surface Evolver Bench ↗

    yhenon

Names used in source tables

Kimi K2.7 Code · Kimi K2.7 Code (Mini-SWE-agent) · Kimi K2.7 Code (OpenHands) · Kimi K2.7 Code (mini-SWE-agent) xhigh · kimi-k2.7-code