Vibeleaderboard
← Benchmark guide

Model results

SWE-bench Live

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.

Evaluation groups

Open a group to see its exact protocol and scores. Different configurations remain separate.

No model rankings are available in this snapshot. Reported results remain available below.

Other reported results

These reports have no model ranking. Open a group for its evidence and the reason positions are withheld.

  • GPT-5.5windows-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-06-06

    Scope · windows split; 16/60 resolved; system Win-agent + GPT-5.5 (Medium); submission evidence https://gith…

    windows split; 16/60 resolved; system Win-agent + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/windows/win-agent/gpt-5.5-medium; publisher verified=True

  • GPT-5.5tsjs-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-07-30

    Scope · tsjs split; 98/204 resolved; system Slingshot-v3.0.0 + GPT-5.5 (Medium); submission evidence https:/…

    tsjs split; 98/204 resolved; system Slingshot-v3.0.0 + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/js_ts/slingshot-agent/20260730-sapient-slingshot-gpt-5.5; publisher verified=False

  • Claude Opus 4.6tsjs-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-07-10

    Scope · tsjs split; 112/204 resolved; system AMI Agent + Claude-4.6-Opus; submission evidence https://github…

    tsjs split; 112/204 resolved; system AMI Agent + Claude-4.6-Opus; submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/js_ts/ami-agent; publisher verified=False

  • GPT-5.5tsjs-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-06-29

    Scope · tsjs split; 77/204 resolved; system Slingshot-v2.6.0 + GPT-5.5 (Medium); submission evidence https:/…

    tsjs split; 77/204 resolved; system Slingshot-v2.6.0 + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/js_ts/slingshot-agent/20260629-sapient-slingshot-gpt-5.5; publisher verified=False

  • GPT-5.5tsjs-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-06-05

    Scope · tsjs split; 87/204 resolved; system Claude Code + GPT-5.5 (Medium); submission evidence https://gith…

    tsjs split; 87/204 resolved; system Claude Code + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/all_languages/claudecode/gpt-5.5-medium; publisher verified=True

  • GPT-5.5tsjs-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-06-05

    Scope · tsjs split; 92/204 resolved; system OpenHands + GPT-5.5 (Medium); submission evidence https://github…

    tsjs split; 92/204 resolved; system OpenHands + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/all_languages/openhands/gpt-5.5-medium; publisher verified=True

  • GPT-5.5tsjs-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-06-05

    Scope · tsjs split; 97/204 resolved; system SWE-agent + GPT-5.5 (Medium); submission evidence https://github…

    tsjs split; 97/204 resolved; system SWE-agent + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/all_languages/sweagent/gpt-5.5-medium; publisher verified=True

  • Claude Opus 4.6rust-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-06-25

    Scope · rust split; 46/94 resolved; system AMI Agent + Claude-4.6-Opus; submission evidence https://github.c…

    rust split; 46/94 resolved; system AMI Agent + Claude-4.6-Opus; submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/rust/ami-agent/20260625-claude-opus-4-6; publisher verified=False

  • GPT-5.5rust-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-06-05

    Scope · rust split; 18/64 resolved; system SWE-agent + GPT-5.5 (Medium); submission evidence https://github.…

    rust split; 18/64 resolved; system SWE-agent + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/all_languages/sweagent/gpt-5.5-medium; publisher verified=True

  • GPT-5.5rust-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-06-05

    Scope · rust split; 19/64 resolved; system OpenHands + GPT-5.5 (Medium); submission evidence https://github.…

    rust split; 19/64 resolved; system OpenHands + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/all_languages/openhands/gpt-5.5-medium; publisher verified=True

  • GPT-5.5rust-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-06-05

    Scope · rust split; 21/64 resolved; system Claude Code + GPT-5.5 (Medium); submission evidence https://githu…

    rust split; 21/64 resolved; system Claude Code + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/all_languages/claudecode/gpt-5.5-medium; publisher verified=True

  • GPT-5.5lite-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-09-03

    Scope · lite split; 186/300 resolved; system agav-agent + GPT-5.5 (Medium); submission evidence https://gith…

    lite split; 186/300 resolved; system agav-agent + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/blob/main/submissions/lite/agav/gpt-5.5; publisher verified=True

  • GPT-5.6 Sollite-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-08-31

    Scope · lite split; 134/300 resolved; system Slingshot-v3.3.0 + GPT-5.6-Sol; submission evidence https://git…

    lite split; 134/300 resolved; system Slingshot-v3.3.0 + GPT-5.6-Sol; submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/lite/sapient-slingshot-agent/v3.3.0/20260831-gpt-5.6-sol; publisher verified=True

  • Claude Opus 4.6lite-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-08-17

    Scope · lite split; 75/300 resolved; system Slingshot-v3.1.0 + Claude-4.6-Opus; submission evidence https://…

    lite split; 75/300 resolved; system Slingshot-v3.1.0 + Claude-4.6-Opus; submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/lite/sapient-slingshot-agent/v3.1.0/20260817-opus-4-6; publisher verified=False

  • Claude Opus 4.6lite-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-06-23

    Scope · lite split; 189/300 resolved; system AMI Agent + Claude-4.6-Opus; submission evidence https://github…

    lite split; 189/300 resolved; system AMI Agent + Claude-4.6-Opus; submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/lite/ami-agent; publisher verified=False

  • GPT-5.6 Soljava-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-09-01

    Scope · java split; 84/160 resolved; system Slingshot-v3.3.0 + GPT-5.6-Sol; submission evidence https://gith…

    java split; 84/160 resolved; system Slingshot-v3.3.0 + GPT-5.6-Sol; submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/java/slingshot-agent/20260901-sapient-slingshot-gpt-5.6-sol; publisher verified=True

  • Claude Opus 4.6java-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-08-17

    Scope · java split; 73/109 resolved; system AMI Agent + Claude-4.6-Opus; submission evidence https://github.…

    java split; 73/109 resolved; system AMI Agent + Claude-4.6-Opus; submission evidence https://github.com/SWE-bench-Live/submission/blob/main/submissions/multilang/java/ami-agent/20260817-v0.7.2-claude-opus-4-6; publisher verified=False

  • GPT-5.5java-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-08-12

    Scope · java split; 45/109 resolved; system Slingshot-v3.1.0 + GPT-5.5 (Medium); submission evidence https:/…

    java split; 45/109 resolved; system Slingshot-v3.1.0 + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/java/slingshot-agent/20260812-sapient-slingshot-gpt-5.5; publisher verified=False

  • GPT-5.5java-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-07-07

    Scope · java split; 40/109 resolved; system Slingshot-v2.6.0 + GPT-5.5 (Medium); submission evidence https:/…

    java split; 40/109 resolved; system Slingshot-v2.6.0 + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/java/slingshot-agent/20260707-sapient-slingshot-gpt-5.5; publisher verified=False

  • GPT-5.5java-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-06-05

    Scope · java split; 46/102 resolved; system Claude Code + GPT-5.5 (Medium); submission evidence https://gith…

    java split; 46/102 resolved; system Claude Code + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/all_languages/claudecode/gpt-5.5-medium; publisher verified=True

  • GPT-5.5java-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-06-05

    Scope · java split; 48/102 resolved; system OpenHands + GPT-5.5 (Medium); submission evidence https://github…

    java split; 48/102 resolved; system OpenHands + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/all_languages/openhands/gpt-5.5-medium; publisher verified=True

  • GPT-5.5java-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-06-05

    Scope · java split; 51/102 resolved; system SWE-agent + GPT-5.5 (Medium); submission evidence https://github…

    java split; 51/102 resolved; system SWE-agent + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/all_languages/sweagent/gpt-5.5-medium; publisher verified=True

  • Claude Sonnet 4.6go-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-07-23

    Scope · go split; 99/138 resolved; system AMI Agent + Claude-4.6-Sonnet; submission evidence https://github.…

    go split; 99/138 resolved; system AMI Agent + Claude-4.6-Sonnet; submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/go/ami-agent/20260723-claude-sonnet-4-6; publisher verified=False

  • Claude Opus 4.6go-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-07-16

    Scope · go split; 103/138 resolved; system AMI Agent + Claude-4.6-Opus; submission evidence https://github.c…

    go split; 103/138 resolved; system AMI Agent + Claude-4.6-Opus; submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/go/ami-agent/20260716-claude-opus-4-6; publisher verified=False

  • GPT-5.5go-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-06-05

    Scope · go split; 25/98 resolved; system OpenHands + GPT-5.5 (Medium); submission evidence https://github.co…

    go split; 25/98 resolved; system OpenHands + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/all_languages/openhands/gpt-5.5-medium; publisher verified=True

  • GPT-5.5go-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-06-05

    Scope · go split; 34/98 resolved; system SWE-agent + GPT-5.5 (Medium); submission evidence https://github.co…

    go split; 34/98 resolved; system SWE-agent + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/all_languages/sweagent/gpt-5.5-medium; publisher verified=True

  • GPT-5.5go-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-06-05

    Scope · go split; 37/98 resolved; system Claude Code + GPT-5.5 (Medium); submission evidence https://github.…

    go split; 37/98 resolved; system Claude Code + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/all_languages/claudecode/gpt-5.5-medium; publisher verified=True

  • GPT-5.5csharp-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-06-05

    Scope · csharp split; 31/78 resolved; system Claude Code + GPT-5.5 (Medium); submission evidence https://git…

    csharp split; 31/78 resolved; system Claude Code + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/all_languages/claudecode/gpt-5.5-medium; publisher verified=True

  • GPT-5.5csharp-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-06-05

    Scope · csharp split; 33/78 resolved; system OpenHands + GPT-5.5 (Medium); submission evidence https://githu…

    csharp split; 33/78 resolved; system OpenHands + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/all_languages/openhands/gpt-5.5-medium; publisher verified=True

  • GPT-5.5csharp-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-06-05

    Scope · csharp split; 35/78 resolved; system SWE-agent + GPT-5.5 (Medium); submission evidence https://githu…

    csharp split; 35/78 resolved; system SWE-agent + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/all_languages/sweagent/gpt-5.5-medium; publisher verified=True

  • GPT-5.5ccpp-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-06-05

    Scope · ccpp split; 22/66 resolved; system OpenHands + GPT-5.5 (Medium); submission evidence https://github.…

    ccpp split; 22/66 resolved; system OpenHands + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/all_languages/openhands/gpt-5.5-medium; publisher verified=True

  • GPT-5.5ccpp-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-06-05

    Scope · ccpp split; 23/66 resolved; system SWE-agent + GPT-5.5 (Medium); submission evidence https://github.…

    ccpp split; 23/66 resolved; system SWE-agent + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/all_languages/sweagent/gpt-5.5-medium; publisher verified=True

  • GPT-5.5ccpp-0605

    SWE-bench Live · SWE-bench Live (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-06-05

    Scope · ccpp split; 25/66 resolved; system Claude Code + GPT-5.5 (Medium); submission evidence https://githu…

    ccpp split; 25/66 resolved; system Claude Code + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/multilang/all_languages/claudecode/gpt-5.5-medium; publisher verified=True

SWE-bench Live model results | VibeLeaderboard