Vibeleaderboard
← Benchmark guide

Model results

SWE-bench

Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.

Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.

Reviewed recommendation and limits

Use Verified as a historical shared-agent reference. Start with the locked public SWE-bench Pro V2 protocol for contemporary repository issue repair.

Historical Verified with mini-SWE-agent; preserve each imported suite and harness. Imported groups below may use different protocols; this review does not certify each run. OpenAI stopped reporting Verified after finding task defects and memorized solutions. Its 59.4% defect finding concerns 138 selected difficult tasks, not the full 500-task set. Imported Epoch runs have their own protocol.

Publisher results OpenAI audit of SWE-bench Verified
← All evaluation groups

SWE-bench Verified

Source
Hugging Face OpenEvals
Version
Not reported
Measurement date
Not reported
Metric
% · Higher is better
Evaluation scope
Latest published official benchmark result aggregated by OpenEvals · result date not supplied

Positions are withheld because at least one result lacks explicit independent provenance or a documented evaluation scope. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

  1. Qwen3.5 397B A17B

    qwen/qwen3.5-397b-a17b-20260216

    76.4%

    View modelEvidence Evidence class unreported

  2. MiniMax M2.5

    minimax/minimax-m2.5-20260211

    75.8%

    View modelEvidence Evidence class unreported

  3. Step 3.5 Flash

    stepfun/step-3.5-flash

    74.4%

    View modelEvidence Evidence class unreported

  4. MiniMax M2.1

    minimax/minimax-m2.1

    74%

    View modelEvidence Evidence class unreported

  5. GLM 4.7

    z-ai/glm-4.7-20251222

    73.8%

    View modelEvidence Evidence class unreported

  6. GLM 5

    z-ai/glm-5-20260211

    72.8%

    View modelEvidence Evidence class unreported

  7. Qwen3.5-27B

    qwen/qwen3.5-27b-20260224

    72.4%

    View modelEvidence Evidence class unreported

  8. Qwen3.5-122B-A10B

    qwen/qwen3.5-122b-a10b-20260224

    72%

    View modelEvidence Evidence class unreported

  9. Kimi K2 Thinking

    moonshotai/kimi-k2-thinking-20251106

    71.3%

    View modelEvidence Evidence class unreported

  10. Kimi K2.5

    moonshotai/kimi-k2.5-0127

    70.8%

    View modelEvidence Evidence class unreported

  11. Qwen3 Coder Next

    qwen/qwen3-coder-next-2025-02-03

    70.6%

    View modelEvidence Evidence class unreported

  12. DeepSeek V3.2

    deepseek/deepseek-v3.2-20251201

    70%

    View modelEvidence Evidence class unreported

  13. MiniMax M2

    minimax/minimax-m2

    69.4%

    View modelEvidence Evidence class unreported

  14. Qwen3.5-35B-A3B

    qwen/qwen3.5-35b-a3b-20260224

    69.2%

    View modelEvidence Evidence class unreported

  15. GLM 4.7 Flash

    z-ai/glm-4.7-flash-20260119

    59.2%

    View modelEvidence Evidence class unreported

  16. gpt-oss-120b

    openai/gpt-oss-120b

    47.9%

    View modelEvidence Evidence class unreported

  17. gpt-oss-20b

    openai/gpt-oss-20b

    37.4%

    View modelEvidence Evidence class unreported
SWE-bench model results | VibeLeaderboard