ARCactiveReasoning
ARC: AI2 Reasoning Challenge
Metric: Accuracy (higher is better)Introduced: 2018
Grade-school science multiple-choice questions partitioned into Easy and Challenge (hard) sets. ARC-Challenge is the standard evaluation variant.
Models ranked
5
tracked on this benchmark
Score band
94.8 – 78.6
best → lowest tracked
Snapshot trend
+5.69
May 28 → Jun 25 · 1 models
Leaderboard
Tracked models ranked by Accuracy (higher is better).
#Model variant and provenanceRelative to leaderScore
1
Llama 3 70B
94.8Version: Not recordedHarness: Not recordedEvaluator: Not recordedObserved: May 28, 2026Confidence: Not recordedSource
2
Nemotron-Labs TwoTower 30B-A3B Base
92.7Version: ARC-Challenge, 25-shot, acc_norm; default TwoTower diffusion decoding at confidence_threshold=0.8, block_size=16, BF16 on 2xH100; evaluator/harness not published on the model cardHarness: Not recordedEvaluator: Not recordedObserved: Jun 25, 2026Confidence: Not recordedSource
3
Gemma 2 27B
88.5Version: Not recordedHarness: Not recordedEvaluator: Not recordedObserved: May 28, 2026Confidence: Not recordedSource
4
Mixtral 8x22B v0.1
86.0Version: Not recordedHarness: Not recordedEvaluator: Not recordedObserved: May 28, 2026Confidence: Not recordedSource
5
Phi-3 Mini 128K
78.6Version: Not recordedHarness: Not recordedEvaluator: Not recordedObserved: May 28, 2026Confidence: Not recordedSource
How to read this benchmark
This benchmark scores models where higher is better. Use scores for directional filtering and shortlisting, not universal quality ranking; then validate pricing, context window, provider availability, and fit for your workload.
Trust this score when
- There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
- The model list covers the same version family you can actually deploy today.
- Top candidates overlap with your required routing and feature requirements.
Be cautious when
- There is only one benchmark snapshot or the dataset appears stale.
- The benchmark metric direction is opposite of your decision objective.
- The score difference between options is narrow and likely within implementation variance.
Related benchmarks
Last reviewed: Apr 15, 2026