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 DirectoryCompare Models

Scoring & Data

Scoring & Data
393 models668 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 BenchmarksReasoningMath

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai

reasoning benchmark

ARC-E Leaderboard

ARC-E (AI2 Reasoning Challenge - Easy Set) is a subset of grade-school level, multiple-choice science questions that requires knowledge and reasoning capabilities. Part of the AI2 Reasoning Challenge dataset containing 5,197 questions that test scientific reasoning and factual knowledge. The Easy Set contains questions that are answerable by retrieval-based and word co-occurrence algorithms, making them more accessible than the Challenge Set.

Updated Aug 17, 2026

Models8
Model coverage8
MetricScore
EvidenceB

On this page

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

ARC-E Ranking

Higher score ranks better on this benchmark.

8 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelGOGemma 2 27BGoogleScore88.6%Percentile100.0%Participants8EvidenceCEvaluatedAug 17, 2026
Rank02ModelGOGemma 2 9BGoogleScore88.0%Percentile85.7%Participants8EvidenceCEvaluatedAug 17, 2026
Rank03ModelNRHermes 3 70BNous ResearchScore83.0%Percentile71.4%Participants8EvidenceCEvaluatedAug 17, 2026
Rank04ModelGOGemma 3n E4BGoogleScore81.6%Percentile57.1%Participants8EvidenceCEvaluatedAug 17, 2026
Rank05ModelGOGemma 3n E4B Instructed LiteRT PreviewGoogleScore81.6%Percentile42.9%Participants8EvidenceCEvaluatedAug 17, 2026
Rank06ModelGOGemma 3n E2BGoogleScore75.8%Percentile28.6%Participants8EvidenceCEvaluatedAug 17, 2026
Rank07ModelGOGemma 3n E2B Instructed LiteRT (Preview)GoogleScore75.8%Percentile14.3%Participants8EvidenceCEvaluatedAug 17, 2026
Rank08ModelBAERNIE 4.5BaiduScore60.7%Percentile0.0%Participants8EvidenceCEvaluatedAug 17, 2026

ARC-E Highlights

The leading models and scores on this benchmark.

Rank #1Gemma 2 27B88.6%Rank #2Gemma 2 9B88.0%Rank #3Hermes 3 70B83.0%Rank #4Gemma 3n E4B81.6%

ARC-E Score Distribution

A closer view of the leading scores on this benchmark.

ARC-E

The Top AI Models for ARC-E

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

Ranking basisThis arc-e AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.

  1. 01
    GO
    Gemma 2 27BGoogle
    Score
    88.6%

    Strengths

    • Ranks #1 of 8 compared models
    • 100th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures ARC-E, not total model capability
  2. 02
    GO
    Gemma 2 9BGoogle
    Score
    88.0%

    Strengths

    • Ranks #2 of 8 compared models
    • 86th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures ARC-E, not total model capability
  3. 03
    NR
    Hermes 3 70BNous Research
    Score
    83.0%

    Strengths

    • Ranks #3 of 8 compared models
    • 71th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures ARC-E, not total model capability
  4. 04
    GO
    Gemma 3n E4BGoogle
    Score
    81.6%
    Speed
    Up to 42 tok/s via Together

    Strengths

    • Ranks #4 of 8 compared models
    • 57th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures ARC-E, not total model capability
  5. 05
    GO
    Gemma 3n E4B Instructed LiteRT PreviewGoogle
    Score
    81.6%

    Strengths

    • Ranks #5 of 8 compared models
    • 43th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures ARC-E, not total model capability

Selection summary

Best AI Models for ARC-E

Gemma 2 27B currently leads ARC-E with 88.6%. 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.

Benchmark rank #1Gemma 2 27B88.6%Benchmark rank #2Gemma 2 9B88.0%Benchmark rank #3Hermes 3 70B83.0%

What is ARC-E?

What ARC-E measures and how its scores work.

ARC-E (AI2 Reasoning Challenge - Easy Set) is a subset of grade-school level, multiple-choice science questions that requires knowledge and reasoning capabilities. Part of the AI2 Reasoning Challenge dataset containing 5,197 questions that test scientific reasoning and factual knowledge. The Easy Set contains questions that are answerable by retrieval-based and word co-occurrence algorithms, making them more accessible than the Challenge Set.

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

Family
ARC-E
Modality
text
Primary category
reasoning
Score direction
higher
LLMBoard eligible
Yes
Evaluation key
arc-e|llm-stats-current

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

FAQ

Common questions about ARC-E.

Which model scores highest on ARC-E?

Gemma 2 27B is currently ranked first with 88.6%.

What does ARC-E measure?

ARC-E (AI2 Reasoning Challenge - Easy Set) is a subset of grade-school level, multiple-choice science questions that requires knowledge and reasoning capabilities. Part of the AI2 Reasoning Challenge dataset containing 5,197 questions that test scientific reasoning and factual knowledge. The Easy Set contains questions that are answerable by retrieval-based and word co-occurrence algorithms, making them more accessible than the Challenge Set.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

8 model results are currently shown.

Does this benchmark affect the overall score?

Yes. This benchmark can contribute to the current LLMBoard capability score.