Results

59 results

SWE-bench Verified — Vals AI mini-swe-agent results
ProviderModelScoreSourceRegistry No.
OpenAIGPT-5.3-Codex (xhigh)78.0%vals.ai for GPT-5.3-Codex (xhigh) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for GPT-5.3-Codex on SWE-bench Verified — Vals AI mini-swe-agent10006
OpenAIGPT-5.4 (xhigh)78.2%vals.ai for GPT-5.4 (xhigh) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for GPT-5.4 on SWE-bench Verified — Vals AI mini-swe-agent10007
OpenAIGPT-5.5 (xhigh)82.6%vals.ai for GPT-5.5 (xhigh) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for GPT-5.5 on SWE-bench Verified — Vals AI mini-swe-agent10008
OpenAIGPT-5.6 Luna (max)93.0%vals.ai for GPT-5.6 Luna (max) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for GPT-5.6 Luna on SWE-bench Verified — Vals AI mini-swe-agent10009
OpenAIGPT-5.6 Sol (max)96.2%vals.ai for GPT-5.6 Sol (max) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for GPT-5.6 Sol on SWE-bench Verified — Vals AI mini-swe-agent10010
OpenAIGPT-5.6 Terra (max)95.4%vals.ai for GPT-5.6 Terra (max) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for GPT-5.6 Terra on SWE-bench Verified — Vals AI mini-swe-agent10011
OpenAIGPT-5.2 (xhigh)75.8%vals.ai for GPT-5.2 (xhigh) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for GPT-5.2 on SWE-bench Verified — Vals AI mini-swe-agent10012
OpenAIGPT-5 (high)69.0%vals.ai for GPT-5 (high) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for GPT-5 on SWE-bench Verified — Vals AI mini-swe-agent10018
OpenAIGPT-5 mini (high)60.8%vals.ai for GPT-5 mini (high) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for GPT-5 mini on SWE-bench Verified — Vals AI mini-swe-agent10019
OpenAIGPT-5.4 mini (xhigh)73.0%vals.ai for GPT-5.4 mini (xhigh) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for GPT-5.4 mini on SWE-bench Verified — Vals AI mini-swe-agent10021
OpenAIGPT-5.4 nano (high)69.8%vals.ai for GPT-5.4 nano (high) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for GPT-5.4 nano on SWE-bench Verified — Vals AI mini-swe-agent10022
DeepSeek AIDeepSeek-V4-Pro (max)77.4%vals.ai for DeepSeek-V4-Pro (max) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for DeepSeek-V4-Pro on SWE-bench Verified — Vals AI mini-swe-agent110002
DeepSeek AIDeepSeek-V3.2 (high)67.6%vals.ai for DeepSeek-V3.2 (high) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for DeepSeek-V3.2 on SWE-bench Verified — Vals AI mini-swe-agent110003
Moonshot AIKimi K2.5 (thinking)70.0%vals.ai for Kimi K2.5 (thinking) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Kimi K2.5 on SWE-bench Verified — Vals AI mini-swe-agent120001
Moonshot AIKimi K2.676.2%vals.ai for Kimi K2.6 on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Kimi K2.6 on SWE-bench Verified — Vals AI mini-swe-agent120002
Moonshot AIKimi K393.4%vals.ai for Kimi K3 on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Kimi K3 on SWE-bench Verified — Vals AI mini-swe-agent120003
Alibaba (Tongyi)Qwen3.6-Plus73.4%vals.ai for Qwen3.6-Plus on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Qwen3.6-Plus on SWE-bench Verified — Vals AI mini-swe-agent130004
Alibaba (Tongyi)Qwen3.7-Max68.8%vals.ai for Qwen3.7-Max on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Qwen3.7-Max on SWE-bench Verified — Vals AI mini-swe-agent130006
Alibaba (Tongyi)Qwen3.8-Max85.6%vals.ai for Qwen3.8-Max on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Qwen3.8-Max on SWE-bench Verified — Vals AI mini-swe-agent130008
MiniMaxMiniMax M2.574.2%vals.ai for MiniMax M2.5 on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for MiniMax M2.5 on SWE-bench Verified — Vals AI mini-swe-agent140001
MiniMaxMiniMax M2.773.8%vals.ai for MiniMax M2.7 on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for MiniMax M2.7 on SWE-bench Verified — Vals AI mini-swe-agent140002
MiniMaxMiniMax M375.0%vals.ai for MiniMax M3 on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for MiniMax M3 on SWE-bench Verified — Vals AI mini-swe-agent140003
Z.aiGLM-4.769.4%vals.ai for GLM-4.7 on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for GLM-4.7 on SWE-bench Verified — Vals AI mini-swe-agent150001
Z.aiGLM-5 (thinking)71.4%vals.ai for GLM-5 (thinking) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for GLM-5 on SWE-bench Verified — Vals AI mini-swe-agent150002
Z.aiGLM-5.176.4%vals.ai for GLM-5.1 on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for GLM-5.1 on SWE-bench Verified — Vals AI mini-swe-agent150003
Z.aiGLM-5.2 (max)82.8%vals.ai for GLM-5.2 (max) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for GLM-5.2 on SWE-bench Verified — Vals AI mini-swe-agent150004
Z.aiGLM-5.3 (max)95.4%vals.ai for GLM-5.3 (max) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for GLM-5.3 on SWE-bench Verified — Vals AI mini-swe-agent150005
Z.aiGLM-5.3-Flash (max)92.0%vals.ai for GLM-5.3-Flash (max) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for GLM-5.3-Flash on SWE-bench Verified — Vals AI mini-swe-agent150006
OpenAIgpt-oss-120b33.6%vals.ai for gpt-oss-120b on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for gpt-oss-120b on SWE-bench Verified — Vals AI mini-swe-agent15001
Thinking Machines LabInkling (0.99)77.6%vals.ai for Inkling (0.99) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Inkling on SWE-bench Verified — Vals AI mini-swe-agent160001
Thinking Machines LabInkling-Small (0.99)82.2%vals.ai for Inkling-Small (0.99) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Inkling-Small on SWE-bench Verified — Vals AI mini-swe-agent160002
AnthropicClaude Sonnet 4.5 (thinking)70.0%vals.ai for Claude Sonnet 4.5 (thinking) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Claude Sonnet 4.5 on SWE-bench Verified — Vals AI mini-swe-agent20005
AnthropicClaude Haiku 4.5 (thinking)66.6%vals.ai for Claude Haiku 4.5 (thinking) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Claude Haiku 4.5 on SWE-bench Verified — Vals AI mini-swe-agent20006
AnthropicClaude Opus 4.5 (thinking)76.4%vals.ai for Claude Opus 4.5 (thinking) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Claude Opus 4.5 on SWE-bench Verified — Vals AI mini-swe-agent20007
AnthropicClaude Opus 4.6 (thinking)78.2%vals.ai for Claude Opus 4.6 (thinking) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Claude Opus 4.6 on SWE-bench Verified — Vals AI mini-swe-agent20008
AnthropicClaude Sonnet 4.677.4%vals.ai for Claude Sonnet 4.6 on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Claude Sonnet 4.6 on SWE-bench Verified — Vals AI mini-swe-agent20009
AnthropicClaude Opus 4.782.0%vals.ai for Claude Opus 4.7 on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Claude Opus 4.7 on SWE-bench Verified — Vals AI mini-swe-agent20010
AnthropicClaude Opus 4.888.6%vals.ai for Claude Opus 4.8 on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Claude Opus 4.8 on SWE-bench Verified — Vals AI mini-swe-agent20011
AnthropicClaude Fable 595.0%vals.ai for Claude Fable 5 on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Claude Fable 5 on SWE-bench Verified — Vals AI mini-swe-agent20012
AnthropicClaude Sonnet 579.6%vals.ai for Claude Sonnet 5 on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Claude Sonnet 5 on SWE-bench Verified — Vals AI mini-swe-agent20013
AnthropicClaude Opus 597.0%vals.ai for Claude Opus 5 on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Claude Opus 5 on SWE-bench Verified — Vals AI mini-swe-agent20014
Google (DeepMind)Gemini 3.8 Flash (high)80.0%vals.ai for Gemini 3.8 Flash (high) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Gemini 3.8 Flash on SWE-bench Verified — Vals AI mini-swe-agent30004
Google (DeepMind)Gemini 3.1 Pro (high)78.8%vals.ai for Gemini 3.1 Pro (high) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Gemini 3.1 Pro on SWE-bench Verified — Vals AI mini-swe-agent30005
Google (DeepMind)Gemini 3.5 Flash (high)78.8%vals.ai for Gemini 3.5 Flash (high) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Gemini 3.5 Flash on SWE-bench Verified — Vals AI mini-swe-agent30006
Google (DeepMind)Gemini 3.6 Flash (high)79.6%vals.ai for Gemini 3.6 Flash (high) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Gemini 3.6 Flash on SWE-bench Verified — Vals AI mini-swe-agent30007
Google (DeepMind)Gemini 3 Pro (high)76.4%vals.ai for Gemini 3 Pro (high) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Gemini 3 Pro on SWE-bench Verified — Vals AI mini-swe-agent30008
Google (DeepMind)Gemini 3 Flash (high)75.0%vals.ai for Gemini 3 Flash (high) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Gemini 3 Flash on SWE-bench Verified — Vals AI mini-swe-agent30009
Google (DeepMind)Gemini 3.7 Flash (high)80.8%vals.ai for Gemini 3.7 Flash (high) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Gemini 3.7 Flash on SWE-bench Verified — Vals AI mini-swe-agent30010
SpaceXAIGrok 4.5 (high)86.6%vals.ai for Grok 4.5 (high) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Grok 4.5 on SWE-bench Verified — Vals AI mini-swe-agent40001
SpaceXAIGrok 4.6 (high)95.6%vals.ai for Grok 4.6 (high) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Grok 4.6 on SWE-bench Verified — Vals AI mini-swe-agent40002