Mercury 2.5
Mercury 2.5 (Inception Labs) was released on Sep 8, 2026. It has no ECI yet: the Epoch AI composite index comes out in a later round after launch, and until then the model holds no position in the ranking.
Where Mercury 2.5 stands out and where it falls behind, by the numbers
Mercury 2.5 has published results on 4 tests compiled by Epoch AI. The yardstick here is its generation: its position among the models released between Dec 12, 2025 and Dec 7, 2026 that took the same test. Against the whole archive, which includes 2023 models, a recent release lands near the top of almost everything, and that says nothing.
Where it stands out
Tests where it sits in the top third of its own generation.
It is not in the top third of its generation on any test with 6 or more models compared.
Where it falls behind
Tests where it sits in the bottom half of its own generation.
See all 4 tests, one by one
| Test | Score | In its generation | Overall | Test record |
|---|---|---|---|---|
| CritPt | 0.0% | #73 / 77 (tied with 4) | #91 / 112 | 32.3% GPT-5.6 Sol |
| SciCode | 38.5% | #71 / 75 | #82 / 104 | 66.9% Claude Opus 5.5 |
| ALE-Bench | 302 | #58 / 59 | #80 / 82 | 2,951 GPT-6 Astra |
| ProofBench | 3.0% | #63 / 66 (tied with 1) | #71 / 74 | 100.0% Claude Fable 5.1 |
For each test, the model's best effort level counts, as in the ranking. Source of the scores: Epoch AI, under CC BY 4.0.
Have you used Mercury 2.5? Rate it
Users' opinion, not measurement: the rating is kept apart from the ranking and does not move anyone's position. One vote per browser, no sign-up, and you can change your rating later.
What people ask about Mercury 2.5
Where do the numbers on this page come from?
From the same three sources as the ranking, all openly licensed: Epoch AI (ECI and individual tests, CC BY 4.0), Arena (human-preference ELO, CC BY 4.0) and LiveBench (overall average, CC BY-SA 4.0). ROO3 does not measure any model. When the page shows a figure published by the maker itself, it appears in the written analysis, labeled as the maker's, and never enters the ranking.
Where each number comes from
Epoch AI, "AI Benchmarking Hub". Published at epoch.ai. Data under the CC BY 4.0 licence, reordered by roo3.co.
The Arena (LMArena) leaderboard, from the public lmarena-ai/leaderboard-dataset on Hugging Face, under the CC BY 4.0 licence. We are not affiliated with the Arena.
LiveBench, by the LiveBench team, published at livebench.ai under the CC BY-SA 4.0 license. The overall average is recomputed by roo3.co with the same formula as the website (average of the categories), and those numbers stay under CC BY-SA 4.0. We are not affiliated with LiveBench.
← See the full ranking