- GDPval (Elo) 1237.2
- τ³-bench Banking 30.2
- MultiChallenge 60.4
- AA-Omniscience-Public (Accuracy) 46.4
- IFBench 76.8
- GPQA Diamond 89.2
- AA-LCR v1.1 77.7
- MRCR v2 75.5
- SWE-Bench Atlas 51.1
- DeepSWE v1 46.3
- BrowseComp+ 55.2
- DeepSearchQA 71.3
Mercury 3
Mercury 3 places in the top three on AA-LCR 1.1.
24
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
Inception Labs Oct 2026
Mercury 3
Closed weights Flagship
No Epoch Capabilities Index score yet
- IFBench 76.8% #17 /70
- AA-Omniscience 46.4% #6 /17
- Legal Research Bench 28.9% #56 /88
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| IFBench | 76.8% | #17 of 70 | Model card | |
| AA-Omniscience | 46.4% | #6 of 17 | Model card | |
| MRCR v2 | 75.5% | #13 of 27 | Model card | |
| MultiChallenge | 60.4% | #19 of 36 | Model card | |
| AA-LCR 1.1 | 77.7% | #3 of 5 | Model card |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GPQA Diamond | 89.2% | #37 of 284 | Model card |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Vibe Code Bench | 60.9% | #55 of 115 | Official leaderboard | |
| SWE Atlas | 51.1% | #7 of 11 | Model card | |
| Code Migration v1.1 | 39.3% | #21 of 29 | Official leaderboard | |
| DeepSWE | 46.3% | #44 of 51 | Model card |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LLM Chess | 1,308 | #11 of 124 | Official leaderboard | |
| τ³-bench Banking | 30.2% | #8 of 20 | Model card | |
| BrowseComp-Plus | 55.2% | #2 of 4 | Model card | |
| DeepSearchQA | 71.3% | #20 of 22 | Model card |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Legal Research Bench | 28.9% | #56 of 88 | Official leaderboard | |
| Tax Agent Bench | 18.2% | #53 of 79 | Official leaderboard | |
| Harvey LAB v1.1 (HLAB-Vals-1.1) | 5.00% | #26 of 33 | Official leaderboard | |
| Vals Legal Index | 63% | #27 of 33 | Official leaderboard | |
| Vals Finance Agent v2.1 | 54.7% | #30 of 35 | Official leaderboard | |
| Vals Index v2.2 | 43.7% | #28 of 32 | Official leaderboard | |
| Vals Finance Index | 47.2% | #31 of 35 | Official leaderboard | |
| Excel Modeling Benchmark v1.1 | 57.9% | #34 of 37 | Official leaderboard | |
| GDPval-AA v2.1 | 1,237 | #8 of 8 | Model card |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OncologyBench | 8.00% | #26 of 30 | Official leaderboard |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.