Benchmarks

9 results across 5 benchmarks

Benchmark results for Gemini 2.5 Flash
BenchmarkScoreSource
GPQA Diamond82.8%storage.googleapis.com for Gemini 2.5 Flash on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab)GPQA Diamond AccuracyReported Technical reportGoogleSelf-reportedGoogle DeepMindRecord for Gemini 2.5 Flash on Graduate-Level Google-Proof Q&A Diamond
GPQA Diamond — Vals AI harnessConfiguration: Vals AI harness: mean of zero-shot and few-shot CoT57.6%vals.ai for Gemini 2.5 Flash on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness (opens in a new tab)Archived copy (opens in a new tab)GPQA Diamond AccuracyReported Benchmark leaderboardVals AIIndependentRecord for Gemini 2.5 Flash on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness
Humanity's Last Exam Full set — Scale AI evaluation12.1%labs.scale.com for Gemini 2.5 Flash on Humanity's Last Exam Full set — Scale AI evaluation (opens in a new tab)Archived copy (opens in a new tab)Humanity's Last Exam AccuracyReported Benchmark leaderboardScale AIIndependentRecord for Gemini 2.5 Flash on Humanity's Last Exam Full set — Scale AI evaluation
Humanity's Last Exam Text only — Scale AI evaluation12.6%labs.scale.com for Gemini 2.5 Flash on Humanity's Last Exam Text only — Scale AI evaluation (opens in a new tab)Archived copy (opens in a new tab)Humanity's Last Exam AccuracyReported Benchmark leaderboardScale AIIndependentRecord for Gemini 2.5 Flash on Humanity's Last Exam Text only — Scale AI evaluation
MMMU79.7%storage.googleapis.com for Gemini 2.5 Flash on Massive Multi-discipline Multimodal Understanding MMMU (opens in a new tab)MMMU AccuracyReported Technical reportGoogleSelf-reportedGoogle DeepMindRecord for Gemini 2.5 Flash on Massive Multi-discipline Multimodal Understanding MMMU
MMMU-Pro Vals AI harnessConfiguration: Vals AI harness68.0%vals.ai for Gemini 2.5 Flash on MMMU-Pro Vals AI harness (opens in a new tab)Archived copy (opens in a new tab)MMMU-Pro accuracySetting: Standard (4 options)Reported Benchmark leaderboardVals AIIndependentRecord for Gemini 2.5 Flash on MMMU-Pro Vals AI harness
MMMU-Pro Vals AI harnessReported as: thinkingConfiguration: Vals AI harness71.9%vals.ai for Gemini 2.5 Flash (thinking) on MMMU-Pro Vals AI harness (opens in a new tab)Archived copy (opens in a new tab)MMMU-Pro accuracySetting: Standard (4 options)Reported Benchmark leaderboardVals AIIndependentRecord for Gemini 2.5 Flash on MMMU-Pro Vals AI harness
SWE-bench Verified48.9%storage.googleapis.com for Gemini 2.5 Flash on SWE-bench Verified (opens in a new tab)Resolved TasksReported Technical reportGoogleSelf-reportedGoogle DeepMindRecord for Gemini 2.5 Flash on SWE-bench Verified
SWE-bench Verified — mini-swe-agentConfiguration: mini-swe-agent harness28.7%github.com for Gemini 2.5 Flash on SWE-bench Verified — mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for Gemini 2.5 Flash on SWE-bench Verified — mini-swe-agent