Capable on Reasoning and Agentic +1 more; limited on Coding and Factuality. Insufficient data on 5 of 10 axes.
| Benchmark | Score | Settings | Source | Verification | Methodology | Measured | Reference |
|---|---|---|---|---|---|---|---|
Artificial Analysis Intelligence Index | 47.00 | — | artificialanalysis.aik2-horizon-375b-a23b | VERIFIED | OTHER | 4h ago | view ↗ |
terminalbenchV21 | 71.91 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 4h ago | — |
aa_agentic_index | 42.78 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 4h ago | — |
aa_lcr | 75.67 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 4h ago | — |
aa_omniscience | -2.97 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 4h ago | — |
aa_coding_index | 61.52 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 4h ago | — |
| 4.57 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 4h ago | — | |
| 46.20 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 4h ago | — | |
gpqa | 87.27 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 4h ago | — |
aa_hle | 31.97 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 4h ago | — |
omniscienceAccuracy | 18.18 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 4h ago | — |
omniscienceNonHallucination | 74.15 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 4h ago | — |
aa_scicode | 40.74 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 4h ago | — |
tauBanking | 34.23 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 4h ago | — |
aa_intelligence_index | 47.28 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 4h ago | — |