Results

27 results

SWE-bench Verified — Epoch AI harness results
ProviderModelScoreSourceRegistry No.
OpenAIGPT-4.148.5%epoch.ai for GPT-4.1 on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for GPT-4.1 on SWE-bench Verified — Epoch AI harness10002
OpenAIOpenAI o3 (medium)62.3%epoch.ai for OpenAI o3 (medium) on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for OpenAI o3 on SWE-bench Verified — Epoch AI harness10003
OpenAIGPT-5.3-Codex (high)74.8%epoch.ai for GPT-5.3-Codex (high) on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for GPT-5.3-Codex on SWE-bench Verified — Epoch AI harness10006
OpenAIGPT-5.4 (high)76.9%epoch.ai for GPT-5.4 (high) on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for GPT-5.4 on SWE-bench Verified — Epoch AI harness10007
OpenAIGPT-5.2 (high)73.8%epoch.ai for GPT-5.2 (high) on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for GPT-5.2 on SWE-bench Verified — Epoch AI harness10012
OpenAIGPT-5 (medium)71.5%epoch.ai for GPT-5 (medium) on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for GPT-5 on SWE-bench Verified — Epoch AI harness10018
OpenAIGPT-5 (high)73.6%epoch.ai for GPT-5 (high) on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for GPT-5 on SWE-bench Verified — Epoch AI harness10018
OpenAIGPT-5 mini (medium)64.7%epoch.ai for GPT-5 mini (medium) on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for GPT-5 mini on SWE-bench Verified — Epoch AI harness10019
DeepSeek AIDeepSeek-V4-Pro (max)77.6%epoch.ai for DeepSeek-V4-Pro (max) on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for DeepSeek-V4-Pro on SWE-bench Verified — Epoch AI harness110002
Moonshot AIKimi K2.573.8%epoch.ai for Kimi K2.5 on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Kimi K2.5 on SWE-bench Verified — Epoch AI harness120001
Moonshot AIKimi K2.676.7%epoch.ai for Kimi K2.6 on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Kimi K2.6 on SWE-bench Verified — Epoch AI harness120002
Alibaba (Tongyi)Qwen3.6-Plus57.9%epoch.ai for Qwen3.6-Plus on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Qwen3.6-Plus on SWE-bench Verified — Epoch AI harness130004
Alibaba (Tongyi)Qwen3.7-Max77.3%epoch.ai for Qwen3.7-Max on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Qwen3.7-Max on SWE-bench Verified — Epoch AI harness130006
Z.aiGLM-572.1%epoch.ai for GLM-5 on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for GLM-5 on SWE-bench Verified — Epoch AI harness150002
Z.aiGLM-5.174.2%epoch.ai for GLM-5.1 on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for GLM-5.1 on SWE-bench Verified — Epoch AI harness150003
Z.aiGLM-5.2 (max)78.7%epoch.ai for GLM-5.2 (max) on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for GLM-5.2 on SWE-bench Verified — Epoch AI harness150004
AnthropicClaude 3.7 Sonnet61.0%epoch.ai for Claude 3.7 Sonnet on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Claude 3.7 Sonnet on SWE-bench Verified — Epoch AI harness20001
AnthropicClaude Opus 470.7%epoch.ai for Claude Opus 4 on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Claude Opus 4 on SWE-bench Verified — Epoch AI harness20002
AnthropicClaude Sonnet 4.571.3%epoch.ai for Claude Sonnet 4.5 on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Claude Sonnet 4.5 on SWE-bench Verified — Epoch AI harness20005
AnthropicClaude Opus 4.576.7%epoch.ai for Claude Opus 4.5 on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Claude Opus 4.5 on SWE-bench Verified — Epoch AI harness20007
AnthropicClaude Opus 4.675.6%epoch.ai for Claude Opus 4.6 on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Claude Opus 4.6 on SWE-bench Verified — Epoch AI harness20008
AnthropicClaude Sonnet 4.675.2%epoch.ai for Claude Sonnet 4.6 on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Claude Sonnet 4.6 on SWE-bench Verified — Epoch AI harness20009
AnthropicClaude Opus 4.7 (max)83.5%epoch.ai for Claude Opus 4.7 (max) on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Claude Opus 4.7 on SWE-bench Verified — Epoch AI harness20010
AnthropicClaude Opus 4.173.3%epoch.ai for Claude Opus 4.1 on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Claude Opus 4.1 on SWE-bench Verified — Epoch AI harness20017
Google (DeepMind)Gemini 3.5 Flash (high)79.3%epoch.ai for Gemini 3.5 Flash (high) on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Gemini 3.5 Flash on SWE-bench Verified — Epoch AI harness30006
Google (DeepMind)Gemini 3 Pro72.9%epoch.ai for Gemini 3 Pro on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Gemini 3 Pro on SWE-bench Verified — Epoch AI harness30008
Google (DeepMind)Gemini 3 Flash75.4%epoch.ai for Gemini 3 Flash on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Gemini 3 Flash on SWE-bench Verified — Epoch AI harness30009