Inception
availableShows if the model has enough results for an index.Mercury 2.5
Mercury 2.5 is a reasoning model from Inception. 14 benchmarks count toward its score, in 6 categories.
IndexOverall score out of 100.48.5 ±5.8
CoverageShare of the index weight with results.85%
SpeedOutput tokens per second.196/s
Input / 1MUS dollars per 1M input tokens.$0.04
Output / 1MUS dollars per 1M output tokens.$0.15
ContextMaximum tokens in one request.260K
EloLMArena rating and rank.N/A
The index is a score out of 100. The ± range shows how much it can change.
CapabilitiesScore per category, out of 100.
Out of 100Results
14 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result as a score out of 100. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| τ³-Bench Tool-Agent-User Evaluation | Agentic | 96.0% | 76.7 | — | — | Sierra Research |
| GPQA Diamond | Knowledge | 79.0% | 51.2 | — | — | David Rein et al. |
| Instruction Following Benchmark | Instruction | 77.0% | 55.6 | — | — | Benchmark authors |
| Artificial Analysis Long Context Reasoning | Reasoning | 68.0% | 55.3 | — | — | Artificial Analysis |
| Scientific Code Benchmark | Coding | 38.0% | 47.8 | — | — | Benchmark authors |
| Terminal-Bench 2.1 | Agentic | 34.1% | 44.2 | — | 21 Sept 2026 | Vals AI |
| DeepSearchQA | Agentic | 34.0% | 24.7 | — | — | Meta AI |
| Artificial Analysis Omniscience Accuracy | Knowledge | 22.0% | 41.1 | — | — | Artificial Analysis |
| SkillsBench | Coding | 18.1% | 38.3 | OpenHands | 11 Sept 2026 | Vals AI |
| Code Migration | Coding | 4.5% | 47.8 | — | 21 Sept 2026 | Vals AI |
| Vibe Code Bench v1.1 | Coding | 3.7% | 43.7 | OpenHands | 21 Sept 2026 | Vals AI |
| ProofBench v1.1 | Math | 3.0% | 50.6 | — | 21 Sept 2026 | Vals AI |
| IOI | Coding | 2.4% | 46.7 | — | 21 Sept 2026 | Vals AI |
| Terminal-Bench 4.0 | Agentic | 0.0% | 59.5 | — | 21 Sept 2026 | Vals AI |
14 benchmarks count, from 14 of 14 results. A grey row does not count. Too few models took that benchmark.