Model comparison
Mercury 2 vs Mistral Large
Mercury 2 is the stronger model overall, scoring 39.1 to 31.9 on the Noometry Index.
Last verified . 15 shared benchmarks.
Mistral AISummary
- They share 15 benchmarks with published results for both. Mercury 2 scores higher in 6 categories and Mistral Large in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mercury 2 leads 53.8 to 40.7.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 12.3% for Mercury 2 and 4.5% for Mistral Large.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $2 / $6 for Mistral Large.
- Mistral Large accepts more context: 131K tokens versus 128K.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| Mercury 2 | Mistral Large | |
|---|---|---|
| Provider | Inception | Mistral AI |
| Noometry Index | 39.1 | 31.9 |
| Released | 2026-02-20 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 128K | 131K |
| Max output | 50K | 16K |
| Input $ / M tokens | $0.25 | $2 |
| Output $ / M tokens | $0.75 | $6 |
| Results tracked | 17 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mercury 2: 33.5 (#255), Mistral Large: 34.3 (#240)
| Benchmark | Mercury 2 | Mistral Large |
|---|---|---|
| SciCode | 38.7% | 36.2% |
| LMArena Coding | 1391 | 1277 |
| ALE-Bench | 785.58 | 264.7 |
| LMArena WebDev | 1171 | — |
| WeirdML | 43.2% | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Not comparable
Mercury 2: —, Mistral Large: 28.6 (#89)
| Benchmark | Mercury 2 | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
Reasoning Mercury 2 leads
Mercury 2: 23.8 (#170), Mistral Large: 15.8 (#310)
| Benchmark | Mercury 2 | Mistral Large |
|---|---|---|
| CritPt | 0.8% | 0% |
| LMArena Hard Prompts | 1362 | 1257 |
| SimpleBench | — | 22.5% |
| LiveBench Reasoning | — | 43.5% |
| DTBench | — | 65.1% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| Epoch Capabilities Index | — | 128.52 |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |
Math Not comparable
Mercury 2: —, Mistral Large: 18.2 (#291)
| Benchmark | Mercury 2 | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 8.5% |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| LMArena Math | — | 1262 |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Mercury 2 leads
Mercury 2: 36.2 (#172), Mistral Large: 30.1 (#230)
| Benchmark | Mercury 2 | Mistral Large |
|---|---|---|
| Vectara Hallucination Rate | 12.3% | 4.5% |
| LMArena Expert | 1358 | 1232 |
| GPQA Diamond | — | 51.3% |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |
Multilingual Mercury 2 leads
Mercury 2: 46.6 (#157), Mistral Large: 40.0 (#219)
| Benchmark | Mercury 2 | Mistral Large |
|---|---|---|
| LMArena Non-English | 1331 | 1237 |
| LMArena Chinese | 1417 | 1240 |
| LMArena Russian | 1304 | 1257 |
| LMArena French | — | 1325 |
| LMArena German | — | 1254 |
| LMArena Japanese | — | 1188 |
| LMArena Korean | — | 1202 |
| LMArena Spanish | — | 1268 |
Instruction Following Mercury 2 leads
Mercury 2: 70.2 (#165), Mistral Large: 67.9 (#191)
| Benchmark | Mercury 2 | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1329 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context Mercury 2 leads
Mercury 2: 40.5 (#154), Mistral Large: 38.3 (#199)
| Benchmark | Mercury 2 | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1330 | 1261 |
Writing & Preference Mercury 2 leads
Mercury 2: 53.8 (#155), Mistral Large: 40.7 (#242)
| Benchmark | Mercury 2 | Mistral Large |
|---|---|---|
| LMArena Text | 1355 | 1266 |
| LMArena Creative Writing | 1289 | 1243 |
| LMArena Multi-Turn | 1358 | 1260 |
| Short-Story Creative Writing | — | 69% |
| EQ-Bench Creative Writing | — | 985 |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is Mercury 2 better than Mistral Large?
Mercury 2 is the stronger model overall, scoring 39.1 to 31.9 on the Noometry Index.
Which is cheaper, Mercury 2 or Mistral Large?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Mistral Large lists at $2 and $6.
Is Mercury 2 or Mistral Large better for coding?
They score almost the same on coding (33.5 vs 34.3); test both on your own repository before choosing.
Which has the bigger context window?
Mistral Large does, with 131K tokens against 128K.
How many benchmarks do Mercury 2 and Mistral Large share?
15 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Mistral Large has 51.