Benchmarks

15 results across 10 benchmarks

Benchmark results for GPT-5.4 mini
BenchmarkScoreSource
Finance Agent Benchmark 2 — October 2026 evaluationEffort: xHigh45.4%vals.ai for GPT-5.4 mini (xhigh) on Finance Agent Benchmark 2 — October 2026 evaluation (opens in a new tab)Archived copy (opens in a new tab)Finance Agent AccuracyReported Benchmark leaderboardVals AIIndependentRecord for GPT-5.4 mini on Finance Agent Benchmark 2 — October 2026 evaluation
GPQA Diamond — Epoch AI harnessEffort: NoneConfiguration: Epoch AI harness64.1%epoch.ai for GPT-5.4 mini (none) on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)GPQA Diamond AccuracyReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for GPT-5.4 mini on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness
GPQA Diamond — Epoch AI harnessEffort: HighConfiguration: Epoch AI harness83.6%epoch.ai for GPT-5.4 mini (high) on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)GPQA Diamond AccuracyReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for GPT-5.4 mini on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness
GPQA Diamond — Epoch AI harnessEffort: xHighConfiguration: Epoch AI harness86.9%epoch.ai for GPT-5.4 mini (xhigh) on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)GPQA Diamond AccuracyReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for GPT-5.4 mini on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness
GPQA Diamond — Vals AI harnessEffort: xHighConfiguration: Vals AI harness: mean of zero-shot and few-shot CoT83.1%vals.ai for GPT-5.4 mini (xhigh) 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 GPT-5.4 mini on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness
HLAB October 2026 evaluationEffort: xHigh0.0%vals.ai for GPT-5.4 mini (xhigh) on Harvey's Legal Agent Benchmark October 2026 evaluation (opens in a new tab)Archived copy (opens in a new tab)HLAB Task Pass RateReported Benchmark leaderboardVals AIIndependentRecord for GPT-5.4 mini on Harvey's Legal Agent Benchmark October 2026 evaluation
MMLU-Pro Original — Vals AI harnessEffort: xHighConfiguration: Vals AI harness84.6%vals.ai for GPT-5.4 mini (xhigh) on MMLU-Pro Original — Vals AI harness (opens in a new tab)Archived copy (opens in a new tab)AccuracyReported Benchmark leaderboardVals AIIndependentRecord for GPT-5.4 mini on MMLU-Pro Original — Vals AI harness
MMMU-Pro Vals AI harnessEffort: xHighConfiguration: Vals AI harness79.2%vals.ai for GPT-5.4 mini (xhigh) 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 GPT-5.4 mini on MMMU-Pro Vals AI harness
SimpleQA Verified Original — Epoch AI harnessEffort: HighConfiguration: Epoch AI harness29.4%epoch.ai for GPT-5.4 mini (high) on SimpleQA Verified Original — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)AccuracyReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for GPT-5.4 mini on SimpleQA Verified Original — Epoch AI harness
SWE-bench Verified — Vals AI mini-swe-agentEffort: xHighConfiguration: mini-swe-agent harness73.0%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-agent
Terminal-Bench 2.0 — Vals AI Terminus 2Effort: HighConfiguration: Terminus-2 harness44.9%vals.ai for GPT-5.4 mini (high) on Terminal-Bench 2.0 — Vals AI Terminus 2 (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardVals AIIndependentRecord for GPT-5.4 mini on Terminal-Bench 2.0 — Vals AI Terminus 2
Terminal-Bench 2.1 — Vals AI Terminus 2Effort: HighConfiguration: Terminus-2 harness54.7%vals.ai for GPT-5.4 mini (high) on Terminal-Bench 2.1 — Vals AI Terminus 2 (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardVals AIIndependentRecord for GPT-5.4 mini on Terminal-Bench 2.1 — Vals AI Terminus 2
Terminal-Bench 4.0 — Vals AI mini-swe-agentEffort: xHighConfiguration: mini-swe-agent harness2.5%vals.ai for GPT-5.4 mini (xhigh) 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 GPT-5.4 mini on Terminal-Bench 4.0 — Vals AI mini-swe-agent
Vals Index 2.1Effort: xHigh33.2%vals.ai for GPT-5.4 mini (xhigh) on Vals Index 2.1 (opens in a new tab)Archived copy (opens in a new tab)Vals Index GDP-weighted AccuracyReported Benchmark leaderboardVals AIIndependentRecord for GPT-5.4 mini on Vals Index 2.1
Vibe Code Bench 1.1 — OpenHands, October 2026 evaluationEffort: xHighConfiguration: OpenHands harness48.0%vals.ai for GPT-5.4 mini (xhigh) on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation (opens in a new tab)Archived copy (opens in a new tab)Vibe Code Bench ScoreReported Benchmark leaderboardVals AIIndependentRecord for GPT-5.4 mini on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation