Benchmarks

20 results across 13 benchmarks

Benchmark results for Claude Haiku 4.5
BenchmarkScoreSource
AutomationBench 1.0.60.5%zapier.com for Claude Haiku 4.5 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 Claude Haiku 4.5 on AutomationBench 1.0.6
Finance Agent Benchmark 2 — October 2026 evaluationReported as: thinking31.0%vals.ai for Claude Haiku 4.5 (thinking) 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 Claude Haiku 4.5 on Finance Agent Benchmark 2 — October 2026 evaluation
GPQA Diamond — Epoch AI harnessConfiguration: Epoch AI harness60.5%epoch.ai for Claude Haiku 4.5 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 Claude Haiku 4.5 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness
GPQA Diamond — Vals AI harnessReported as: thinkingConfiguration: Vals AI harness: mean of zero-shot and few-shot CoT72.2%vals.ai for Claude Haiku 4.5 (thinking) 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 Claude Haiku 4.5 on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness
HLAB October 2026 evaluationReported as: thinking0.8%vals.ai for Claude Haiku 4.5 (thinking) 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 Claude Haiku 4.5 on Harvey's Legal Agent Benchmark October 2026 evaluation
MCP Atlas Public, April 2026 update40.2%labs.scale.com for Claude Haiku 4.5 on MCP Atlas Public, April 2026 update (opens in a new tab)Pass rateReported Benchmark leaderboardScale AIIndependentRecord for Claude Haiku 4.5 on MCP Atlas Public, April 2026 update
MMLU-Pro Original — Vals AI harnessReported as: thinkingConfiguration: Vals AI harness78.7%vals.ai for Claude Haiku 4.5 (thinking) on MMLU-Pro Original — Vals AI harness (opens in a new tab)Archived copy (opens in a new tab)AccuracyReported Benchmark leaderboardVals AIIndependentRecord for Claude Haiku 4.5 on MMLU-Pro Original — Vals AI harness
MMMU-Pro Vals AI harnessReported as: thinkingConfiguration: Vals AI harness46.1%vals.ai for Claude Haiku 4.5 (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 Claude Haiku 4.5 on MMMU-Pro Vals AI harness
SimpleQA Verified Original — Epoch AI harnessConfiguration: Epoch AI harness13.2%epoch.ai for Claude Haiku 4.5 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 Claude Haiku 4.5 on SimpleQA Verified Original — Epoch AI harness
SWE-bench Multilingual — mini-swe-agentConfiguration: mini-swe-agent harness64.7%github.com for Claude Haiku 4.5 on SWE-bench Multilingual — mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for Claude Haiku 4.5 on SWE-bench Multilingual — mini-swe-agent
SWE-bench VerifiedReported as: extended thinking (128K)73.3%anthropic.com for Claude Haiku 4.5 (extended thinking (128K)) on SWE-bench Verified (opens in a new tab)Resolved TasksReported Launch postAnthropicSelf-reportedRecord for Claude Haiku 4.5 on SWE-bench Verified
SWE-bench Verified — mini-swe-agentEffort: HighConfiguration: mini-swe-agent harness66.6%github.com for Claude Haiku 4.5 (high) 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 Claude Haiku 4.5 on SWE-bench Verified — mini-swe-agent
SWE-bench Verified — Vals AI mini-swe-agentReported as: thinkingConfiguration: mini-swe-agent harness66.6%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-agent
SWE-bench Pro Public — Scale AI SWE-AgentConfiguration: SWE-Agent harness, 250 turns, uncapped cost39.5%labs.scale.com for Claude Haiku 4.5 on SWE-bench Pro Public — Scale AI SWE-Agent (opens in a new tab)Archived copy (opens in a new tab)Public tasks resolvedReported Benchmark leaderboardScale AIIndependentRecord for Claude Haiku 4.5 on SWE-bench Pro Public — Scale AI SWE-Agent
Terminal-Bench 2.0Effort: NoneReported as: no thinking40.2%anthropic.com for Claude Haiku 4.5 (no thinking) on Terminal-Bench 2.0 (opens in a new tab)Terminal-Bench AccuracyReported Launch postAnthropicSelf-reportedRecord for Claude Haiku 4.5 on Terminal-Bench 2.0
Terminal-Bench 2.0Reported as: extended thinking (32K)41.8%anthropic.com for Claude Haiku 4.5 (extended thinking (32K)) on Terminal-Bench 2.0 (opens in a new tab)Terminal-Bench AccuracyReported Launch postAnthropicSelf-reportedRecord for Claude Haiku 4.5 on Terminal-Bench 2.0
Terminal-Bench 2.0 — Vals AI Terminus 2Reported as: thinkingConfiguration: Terminus-2 harness38.2%vals.ai for Claude Haiku 4.5 (thinking) 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 Claude Haiku 4.5 on Terminal-Bench 2.0 — Vals AI Terminus 2
Terminal-Bench 2.1 — Vals AI Terminus 2Reported as: thinkingConfiguration: Terminus-2 harness43.8%vals.ai for Claude Haiku 4.5 (thinking) 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 Claude Haiku 4.5 on Terminal-Bench 2.1 — Vals AI Terminus 2
Toolathlon Original26.2%toolathlon.xyz for Claude Haiku 4.5 on Toolathlon Original (opens in a new tab)Archived copy (opens in a new tab)Tasks completedReported Benchmark leaderboardToolathlonIndependentToolathlon AuthorsRecord for Claude Haiku 4.5 on Toolathlon Original
Vibe Code Bench 1.1 — OpenHands, October 2026 evaluationReported as: thinkingConfiguration: OpenHands harness11.4%vals.ai for Claude Haiku 4.5 (thinking) 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 Claude Haiku 4.5 on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation