reasoning benchmark
ARC-C Leaderboard
The AI2 Reasoning Challenge (ARC) Challenge Set is a multiple-choice question-answering benchmark containing grade-school level science questions that require advanced reasoning capabilities. ARC-C specifically contains questions that were answered incorrectly by both retrieval-based and word co-occurrence algorithms, making it a particularly challenging subset designed to test commonsense reasoning abilities in AI systems.
Updated Aug 17, 2026
Models34
Model coverage34
MetricScore
EvidenceB
ARC-C Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelXI | Score97.2% | Percentile100.0% | Participants34 | EvidenceC | Evaluated |
| Rank02 | ModelME | Score96.9% | Percentile97.0% | Participants34 | EvidenceC | Evaluated |
| Rank03 | ModelAN | Score96.4% | Percentile93.9% | Participants34 | EvidenceC | Evaluated |
| Rank04 | ModelME | Score94.8% | Percentile90.9% | Participants34 | EvidenceC | Evaluated |
| Rank05 | ModelAM Nova ProAmazon | Score94.8% | Percentile87.9% | Participants34 | EvidenceC | Evaluated |
| Rank06 | ModelAN | Score93.2% | Percentile84.8% | Participants34 | EvidenceC | Evaluated |
| Rank07 | ModelAL | Score93.0% | Percentile81.8% | Participants34 | EvidenceC | Evaluated |
| Rank08 | ModelAMNova LiteAmazon | Score92.4% | Percentile78.8% | Participants34 | EvidenceC | Evaluated |
| Rank09 | ModelMA | Score91.3% | Percentile75.8% | Participants34 | EvidenceC | Evaluated |
| Rank10 | ModelMI | Score91.0% | Percentile72.7% | Participants34 | EvidenceC | Evaluated |
| Rank11 | ModelAMNova MicroAmazon | Score90.2% | Percentile69.7% | Participants34 | EvidenceC | Evaluated |
| Rank12 | ModelAN | Score89.2% | Percentile66.7% | Participants34 | EvidenceC | Evaluated |
| Rank13 | ModelAL | Score85.7% | Percentile63.6% | Participants34 | EvidenceC | Evaluated |
| Rank14 | ModelMI | Score84.6% | Percentile60.6% | Participants34 | EvidenceC | Evaluated |
| Rank15 | ModelMI | Score83.7% | Percentile57.6% | Participants34 | EvidenceC | Evaluated |
| Rank16 | ModelME | Score83.4% | Percentile54.5% | Participants34 | EvidenceC | Evaluated |
| Rank17 | ModelME | Score78.6% | Percentile51.5% | Participants34 | EvidenceC | Evaluated |
| Rank18 | ModelMA | Score71.9% | Percentile48.5% | Participants34 | EvidenceC | Evaluated |
| Rank19 | ModelGO | Score71.4% | Percentile45.5% | Participants34 | EvidenceC | Evaluated |
| Rank20 | ModelCO | Score71.0% | Percentile42.4% | Participants34 | EvidenceC | Evaluated |
| Rank21 | ModelAC | Score70.5% | Percentile39.4% | Participants34 | EvidenceC | Evaluated |
| Rank22 | ModelAC | Score70.4% | Percentile36.4% | Participants34 | EvidenceC | Evaluated |
| Rank23 | ModelNV | Score69.2% | Percentile33.3% | Participants34 | EvidenceC | Evaluated |
| Rank24 | ModelAC | Score68.9% | Percentile30.3% | Participants34 | EvidenceC | Evaluated |
| Rank25 | ModelGO | Score68.4% | Percentile27.3% | Participants34 | EvidenceC | Evaluated |
| Rank26 | ModelAC | Score67.3% | Percentile24.2% | Participants34 | EvidenceC | Evaluated |
| Rank27 | ModelNR | Score65.5% | Percentile21.2% | Participants34 | EvidenceC | Evaluated |
| Rank28 | ModelGO | Score61.6% | Percentile18.2% | Participants34 | EvidenceC | Evaluated |
| Rank29 | ModelGO | Score61.6% | Percentile15.2% | Participants34 | EvidenceC | Evaluated |
| Rank30 | ModelAC | Score60.9% | Percentile12.1% | Participants34 | EvidenceC | Evaluated |
| Rank31 | ModelGO | Score51.7% | Percentile9.1% | Participants34 | EvidenceC | Evaluated |
| Rank32 | ModelGO | Score51.7% | Percentile6.1% | Participants34 | EvidenceC | Evaluated |
| Rank33 | ModelIB | Score50.8% | Percentile3.0% | Participants34 | EvidenceC | Evaluated |
| Rank34 | ModelBA | Score40.6% | Percentile0.0% | Participants34 | EvidenceC | Evaluated |
ARC-C Highlights
The leading models and scores on this benchmark.
ARC-C Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for ARC-C
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis arc-c 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.
- 01XIMiMo-V2.5-ProXiaomi
- Score
- 97.2%
- Price
- $0.43 input / $0.87 output per 1M tokens
- Speed
- Up to 69 tok/s via Novita
Strengths
- Ranks #1 of 34 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures ARC-C, not total model capability
- 02ME
- Score
- 96.9%
- Speed
- Up to 100 tok/s via Bedrock
Strengths
- Ranks #2 of 34 compared models
- 97th percentile on this benchmark
- C evidence result
Considerations
- This result measures ARC-C, not total model capability
- 03ANClaude 3 OpusAnthropic
- Score
- 96.4%
- Speed
- Up to 120 tok/s via Bedrock
Strengths
- Ranks #3 of 34 compared models
- 94th percentile on this benchmark
- C evidence result
Considerations
- This result measures ARC-C, not total model capability
- 04ME
- Score
- 94.8%
- Speed
- Up to 1,204 tok/s via Cerebras
Strengths
- Ranks #4 of 34 compared models
- 91th percentile on this benchmark
- C evidence result
Considerations
- This result measures ARC-C, not total model capability
- 05AMNova ProAmazon
- Score
- 94.8%
- Price
- $0.80 input / $3.2 output per 1M tokens
- Speed
- Up to 100 tok/s via Bedrock
Strengths
- Ranks #5 of 34 compared models
- 88th percentile on this benchmark
- C evidence result
Considerations
- This result measures ARC-C, not total model capability
Selection summary
Best AI Models for ARC-C
MiMo-V2.5-Pro currently leads ARC-C with 97.2%. 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.
What is ARC-C?
What ARC-C measures and how its scores work.
The AI2 Reasoning Challenge (ARC) Challenge Set is a multiple-choice question-answering benchmark containing grade-school level science questions that require advanced reasoning capabilities. ARC-C specifically contains questions that were answered incorrectly by both retrieval-based and word co-occurrence algorithms, making it a particularly challenging subset designed to test commonsense reasoning abilities in AI systems.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- ARC-C
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- arc-c|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about ARC-C.
Which model scores highest on ARC-C?
MiMo-V2.5-Pro is currently ranked first with 97.2%.
What does ARC-C measure?
The AI2 Reasoning Challenge (ARC) Challenge Set is a multiple-choice question-answering benchmark containing grade-school level science questions that require advanced reasoning capabilities. ARC-C specifically contains questions that were answered incorrectly by both retrieval-based and word co-occurrence algorithms, making it a particularly challenging subset designed to test commonsense reasoning abilities in AI systems.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
34 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.