llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model Directory

Scoring & Data

Scoring & Data
1224 models729 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

language benchmark

BIG-Bench Hard Leaderboard

BIG-Bench Hard (BBH) is a subset of 23 challenging BIG-Bench tasks with 6,511 evaluation examples covering multiple forms of multi-step reasoning.

Updated Sep 5, 2026

Models21
Model coverage21
MetricScore
EvidenceB

On this page

  • Ranking
  • Highlights
  • Distribution
  • Top models
  • About
  • FAQ

BIG-Bench Hard Ranking

Higher score ranks better on this benchmark.

21 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelANClaude 3.5 SonnetAnthropicScore93.10%Percentile100.00%Participants21EvidenceCEvaluatedSep 8, 2026
Rank02ModelANClaude 3.5 SonnetAnthropicScore93.10%Percentile95.00%Participants21EvidenceCEvaluatedSep 8, 2026
Rank03ModelGOGemini 1.5 ProGoogleScore89.20%Percentile90.00%Participants21EvidenceCEvaluatedSep 8, 2026
Rank04ModelGOGemma 3 27BGoogleScore87.60%Percentile85.00%Participants21EvidenceCEvaluatedSep 8, 2026
Rank05ModelANClaude 3 OpusAnthropicScore86.80%Percentile80.00%Participants21EvidenceCEvaluatedSep 8, 2026
Rank06ModelGOGemma 3 12BGoogleScore85.70%Percentile75.00%Participants21EvidenceCEvaluatedSep 8, 2026
Rank07ModelGOGemini 1.5 FlashGoogleScore85.50%Percentile70.00%Participants21EvidenceCEvaluatedSep 8, 2026
Rank08ModelANClaude 3 SonnetAnthropicScore82.90%Percentile65.00%Participants21EvidenceCEvaluatedSep 8, 2026
Rank09ModelMIPhi-3.5-MoE-instructMicrosoftScore79.10%Percentile60.00%Participants21EvidenceCEvaluatedSep 8, 2026
Rank10ModelANClaude 3 HaikuAnthropicScore73.70%Percentile55.00%Participants21EvidenceCEvaluatedSep 8, 2026
Rank11ModelGOGemma 3 4BGoogleScore72.20%Percentile50.00%Participants21EvidenceCEvaluatedSep 8, 2026
Rank12ModelMIPhi 4 MiniMicrosoftScore70.40%Percentile45.00%Participants21EvidenceCEvaluatedSep 8, 2026
Rank13ModelIBGranite 3.3 8B BaseIBMScore69.13%Percentile40.00%Participants21EvidenceCEvaluatedSep 8, 2026
Rank14ModelIBGranite 3.3 8B InstructIBMScore69.13%Percentile35.00%Participants21EvidenceCEvaluatedSep 8, 2026
Rank15ModelMIPhi-3.5-mini-instructMicrosoftScore69.00%Percentile30.00%Participants21EvidenceCEvaluatedSep 8, 2026
Rank16ModelIBIBM Granite 4.0 Tiny PreviewIBMScore55.70%Percentile25.00%Participants21EvidenceCEvaluatedSep 8, 2026
Rank17ModelGOGemma 3n E4BGoogleScore52.90%Percentile20.00%Participants21EvidenceCEvaluatedSep 8, 2026
Rank18ModelGOGemma 3n E4B Instructed LiteRT PreviewGoogleScore52.90%Percentile15.00%Participants21EvidenceCEvaluatedSep 8, 2026
Rank19ModelGOGemma 3n E2BGoogleScore44.30%Percentile10.00%Participants21EvidenceCEvaluatedSep 8, 2026
Rank20ModelGOGemma 3n E2B Instructed LiteRT (Preview)GoogleScore44.30%Percentile5.00%Participants21EvidenceCEvaluatedSep 8, 2026
Rank21ModelGOGemma 3 1BGoogleScore39.10%Percentile0.00%Participants21EvidenceCEvaluatedSep 8, 2026

BIG-Bench Hard Highlights

The leading models and scores on this benchmark.

BIG-Bench Hard Score Distribution

A closer view of the leading scores on this benchmark.

BIG-Bench Hard

The Top AI Models for BIG-Bench Hard

The first five results on this benchmark, with official price and output speed added where the model identity can be matched.

What is BIG-Bench Hard?

What BIG-Bench Hard measures and how its scores work.

BIG-Bench Hard (BBH) is a language benchmark consisting of 23 BIG-Bench tasks selected because prior language model evaluations did not outperform average human-rater performance.

It measures Score as a ratio across arithmetic, logical, geometric, and temporal reasoning, language understanding, causal judgment, object counting, navigation, pattern recognition, and complex problem solving.

Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.

Family
BIG-Bench Hard
Modality
text
Primary category
language
Score direction
higher
LLMBoard eligible
No
Evaluation key
overall

LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.

FAQ

Common questions about BIG-Bench Hard.

Which model scores highest on BIG-Bench Hard?

Claude 3.5 Sonnet is currently ranked first with 93.10%.

What are the top three models on BIG-Bench Hard?

The current leaders are Claude 3.5 Sonnet (93.10%), Claude 3.5 Sonnet (93.10%), and Gemini 1.5 Pro (89.20%).

Which BIG-Bench Hard model has the lowest official input price?

Phi 4 Mini has the lowest matched official input price at $0.08 input / $0.30 output per 1M tokens.

Which models are fastest among BIG-Bench Hard results?

The fastest matched records are Gemini 1.5 Flash (150.00 tok/s via Google), Claude 3.5 Sonnet (100.00 tok/s via Anthropic), and Claude 3 Opus (100.00 tok/s via Anthropic).

Does the highest score result prove overall model quality?

No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.

What does BIG-Bench Hard measure?

It measures Score as a ratio across arithmetic, logical, geometric, and temporal reasoning, language understanding, causal judgment, object counting, navigation, pattern recognition, and complex problem solving.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

21 model results are currently shown.

Does this benchmark affect the overall score?

No. This benchmark is shown for reference but does not contribute to the overall score.

Rank #1Claude 3.5 Sonnet93.10%
Rank #2Claude 3.5 Sonnet93.10%
Rank #3Gemini 1.5 Pro89.20%
Rank #4Gemma 3 27B87.60%

Ranking basisThis big-bench hard AI model leaderboard uses descending score in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.

  1. 01
    AN
    Claude 3.5 SonnetAnthropic
    Score
    93.10%
    Speed
    Up to 42.00 tok/s via Google

    Strengths

    • Ranks #1 of 21 compared models
    • 100th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures BIG-Bench Hard, not total model capability
  2. 02
    AN
    Claude 3.5 SonnetAnthropic
    Score
    93.10%
    Speed
    Up to 100.00 tok/s via Anthropic

    Strengths

    • Ranks #2 of 21 compared models
    • 95th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures BIG-Bench Hard, not total model capability
  3. 03
    GO
    Google
    Score
    89.20%
    Speed
    Up to 85.00 tok/s via Google

    Strengths

    • Ranks #3 of 21 compared models
    • 90th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures BIG-Bench Hard, not total model capability
  4. 04
    GO
    Google
    Score
    87.60%
    Speed
    Up to 33.00 tok/s via DeepInfra

    Strengths

    • Ranks #4 of 21 compared models
    • 85th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures BIG-Bench Hard, not total model capability
  5. 05
    AN
    Anthropic
    Score
    86.80%
    Speed
    Up to 100.00 tok/s via Anthropic

    Strengths

    • Ranks #5 of 21 compared models
    • 80th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures BIG-Bench Hard, not total model capability

Selection summary

Best AI Models for BIG-Bench Hard

Claude 3.5 Sonnet currently leads BIG-Bench Hard with 93.10%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price, and runtime.

Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.

Gemini 1.5 Pro
Gemma 3 27B
Claude 3 Opus
Benchmark rank #1Claude 3.5 Sonnet93.10% · Up to 42.00 tok/s via Google
Benchmark rank #2Claude 3.5 Sonnet93.10% · Up to 100.00 tok/s via Anthropic
Benchmark rank #3Gemini 1.5 Pro89.20% · Up to 85.00 tok/s via Google