Benchmarks

22 results across 18 benchmarks

Benchmark results for Gemini 4 Argon
BenchmarkScoreSource
Agent's Last Exam ALE-V1 — ALE-Claw, 5hEffort: MaxReported as: highest thinking settingsConfiguration: ALE-Claw harness, 5h39.5%deepmind.google for Gemini 4 Argon (highest thinking settings) on Agent's Last Exam ALE-V1 — ALE-Claw, 5h (opens in a new tab)Agent's Last Exam Binary Pass RateReported Evaluation methodologyGoogle DeepMindSelf-reportedRecord for Gemini 4 Argon on Agent's Last Exam ALE-V1 — ALE-Claw, 5h
APEX-Agents OriginalEffort: High82.4%mercor.com for Gemini 4 Argon (high) on APEX-Agents Original (opens in a new tab)Archived copy (opens in a new tab)Pass rateReported Benchmark leaderboardMercorIndependentRecord for Gemini 4 Argon on APEX-Agents Original
AutomationBench 1.0.6Effort: Medium50.1%zapier.com for Gemini 4 Argon (medium) on AutomationBench 1.0.6 (opens in a new tab)Archived copy (opens in a new tab)Task pass rateReported Benchmark leaderboardZapierIndependentZapier AutomationBench TeamRecord for Gemini 4 Argon on AutomationBench 1.0.6
AutomationBench 1.0.6Effort: High51.3%deepmind.google for Gemini 4 Argon (high) on AutomationBench 1.0.6 (opens in a new tab)Task pass rateReported Evaluation methodologyGoogle DeepMindSelf-reportedZapier AutomationBench TeamRecord for Gemini 4 Argon on AutomationBench 1.0.6
Chartography No tools — September 2026 leaderboardEffort: HighConfiguration: No tools71.6%deepmind.google for Gemini 4 Argon (high) on Chartography No tools — September 2026 leaderboard (opens in a new tab)Chartography Pass@1Reported Evaluation methodologyGoogle DeepMindSelf-reportedSurge AIRecord for Gemini 4 Argon on Chartography No tools — September 2026 leaderboard
CWE-bench 1Effort: MaxReported as: highest thinking settings68.0%deepmind.google for Gemini 4 Argon (highest thinking settings) on CWE-bench 1 (opens in a new tab)CWE-bench Programmatic Pass@1Reported Evaluation methodologyGoogle DeepMindSelf-reportedCollinear AIRecord for Gemini 4 Argon on CWE-bench 1
DeepSWE 1.1 — mini-swe-agentEffort: MaxReported as: highest thinking settingsConfiguration: mini-swe-agent harness77.9%deepmind.google for Gemini 4 Argon (highest thinking settings) on DeepSWE 1.1 — mini-swe-agent (opens in a new tab)DeepSWE Pass@1Reported Evaluation methodologyGoogle DeepMindSelf-reportedRecord for Gemini 4 Argon on DeepSWE 1.1 — mini-swe-agent
Finance Agent Benchmark 2 — September 2026 evaluationEffort: High65.4%deepmind.google for Gemini 4 Argon (high) on Finance Agent Benchmark 2 — September 2026 evaluation (opens in a new tab)Finance Agent AccuracyReported Evaluation methodologyGoogle DeepMindSelf-reportedVals AIRecord for Gemini 4 Argon on Finance Agent Benchmark 2 — September 2026 evaluation
FrontierSWE 2 — September 2026 evaluationEffort: MaxReported as: highest thinking settings55.0%deepmind.google for Gemini 4 Argon (highest thinking settings) on FrontierSWE 2 — September 2026 evaluation (opens in a new tab)FrontierSWE ScoreReported Evaluation methodologyGoogle DeepMindSelf-reportedProximalRecord for Gemini 4 Argon on FrontierSWE 2 — September 2026 evaluation
GraphWalks 256k to 1M — BFS, 200 itemsEffort: MaxReported as: highest thinking settings84.2%deepmind.google for Gemini 4 Argon (highest thinking settings) on GraphWalks 256k to 1M — BFS, 200 items (opens in a new tab)GraphWalks BFS F1Reported Evaluation methodologyGoogle DeepMindSelf-reportedRecord for Gemini 4 Argon on GraphWalks 256k to 1M — BFS, 200 items
GraphWalks Up to 128k — BFS, 650 itemsEffort: MaxReported as: highest thinking settings99.7%deepmind.google for Gemini 4 Argon (highest thinking settings) on GraphWalks Up to 128k — BFS, 650 items (opens in a new tab)GraphWalks BFS F1Reported Evaluation methodologyGoogle DeepMindSelf-reportedRecord for Gemini 4 Argon on GraphWalks Up to 128k — BFS, 650 items
HLAB September 2026 evaluationEffort: High19.6%deepmind.google for Gemini 4 Argon (high) on Harvey's Legal Agent Benchmark September 2026 evaluation (opens in a new tab)HLAB Task Pass RateReported Evaluation methodologyGoogle DeepMindSelf-reportedVals AIRecord for Gemini 4 Argon on Harvey's Legal Agent Benchmark September 2026 evaluation
LABBench2 Terminal and internet — September 2026 evaluationEffort: MaxReported as: highest thinking settingsConfiguration: Terminal and internet88.8%deepmind.google for Gemini 4 Argon (highest thinking settings) on LABBench2 Terminal and internet — September 2026 evaluation (opens in a new tab)LABBench2 AccuracyReported Evaluation methodologyGoogle DeepMindSelf-reportedRecord for Gemini 4 Argon on LABBench2 Terminal and internet — September 2026 evaluation
LVBench 1 FPS — No toolsEffort: MaxReported as: highest thinking settingsConfiguration: No tools91.7%deepmind.google for Gemini 4 Argon (highest thinking settings) on LVBench 1 FPS — No tools (opens in a new tab)LVBench AccuracyReported Evaluation methodologyGoogle DeepMindSelf-reportedRecord for Gemini 4 Argon on LVBench 1 FPS — No tools
OSWorld 2.0 v2026.08.08 Offline — Partial, max of 3 runsEffort: MaxReported as: highest thinking settings69.2%deepmind.google for Gemini 4 Argon (highest thinking settings) on OSWorld 2.0 v2026.08.08 Offline — Partial, max of 3 runs (opens in a new tab)OSWorld Partial ScoreReported Evaluation methodologyGoogle DeepMindSelf-reportedRecord for Gemini 4 Argon on OSWorld 2.0 v2026.08.08 Offline — Partial, max of 3 runs
PostTrainBench 1.1 — OpenCodeEffort: MaxReported as: highest thinking settingsConfiguration: OpenCode harness45.3%deepmind.google for Gemini 4 Argon (highest thinking settings) on PostTrainBench 1.1 — OpenCode (opens in a new tab)PostTrainBench Weighted AggregateReported Evaluation methodologyGoogle DeepMindSelf-reportedRecord for Gemini 4 Argon on PostTrainBench 1.1 — OpenCode
Riemann-bench September 2026 leaderboardEffort: MaxReported as: highest thinking settings76.0%deepmind.google for Gemini 4 Argon (highest thinking settings) on Riemann-bench September 2026 leaderboard (opens in a new tab)Riemann-bench Pass@1Reported Evaluation methodologyGoogle DeepMindSelf-reportedSurge AIRecord for Gemini 4 Argon on Riemann-bench September 2026 leaderboard
Terminal-Bench 4.0Effort: MaxReported as: highest thinking settings57.4%deepmind.google for Gemini 4 Argon (highest thinking settings) on Terminal-Bench 4.0 (opens in a new tab)Terminal-Bench AccuracyReported Evaluation methodologyGoogle DeepMindSelf-reportedRecord for Gemini 4 Argon on Terminal-Bench 4.0
Terminal-Bench 4.0 — Vals AI mini-swe-agentEffort: HighConfiguration: mini-swe-agent harness57.6%vals.ai for Gemini 4 Argon (high) on Terminal-Bench 4.0 — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardVals AIIndependentRecord for Gemini 4 Argon on Terminal-Bench 4.0 — Vals AI mini-swe-agent
Terminal-Bench Science 0.1 — 6x verifier timeoutEffort: MaxReported as: highest thinking settingsConfiguration: 6x verifier timeout57.6%deepmind.google for Gemini 4 Argon (highest thinking settings) on Terminal-Bench Science 0.1 — 6x verifier timeout (opens in a new tab)Terminal-Bench AccuracyReported Evaluation methodologyGoogle DeepMindSelf-reportedRecord for Gemini 4 Argon on Terminal-Bench Science 0.1 — 6x verifier timeout
Vals Index 2.1Effort: High68.9%deepmind.google for Gemini 4 Argon (high) on Vals Index 2.1 (opens in a new tab)Vals Index GDP-weighted AccuracyReported Evaluation methodologyGoogle DeepMindSelf-reportedVals AIRecord for Gemini 4 Argon on Vals Index 2.1
Vibe Code Bench 1.1 — OpenHands, September 2026 evaluationEffort: HighConfiguration: OpenHands harness91.9%deepmind.google for Gemini 4 Argon (high) on Vibe Code Bench 1.1 — OpenHands, September 2026 evaluation (opens in a new tab)Vibe Code Bench ScoreReported Evaluation methodologyGoogle DeepMindSelf-reportedVals AIRecord for Gemini 4 Argon on Vibe Code Bench 1.1 — OpenHands, September 2026 evaluation