Model comparison
Mercury 2.5 vs Mistral Medium
Mistral Medium is the stronger model overall, scoring 36.3 to 33.5 on the Noometry Index. Mercury 2.5 costs 44× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
Mistral AISummary
- They share 4 benchmarks with published results for both. Mercury 2.5 scores higher in 1 category and Mistral Medium in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in coding, where Mercury 2.5 leads 39.5 to 34.2.
- The biggest single-benchmark swing is ProofBench: 3% for Mercury 2.5 and 9% for Mistral Medium.
- Mercury 2.5 is cheaper at $0.04 / $0.15 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Mistral Medium accepts more context: 262K tokens versus 260K.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| Mercury 2.5 | Mistral Medium | |
|---|---|---|
| Provider | Inception | Mistral AI |
| Noometry Index | 33.5 | 36.3 |
| Released | 2026-09-08 | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | 260K | 262K |
| Max output | 66K | 262K |
| Input $ / M tokens | $0.04 | $1.50 |
| Output $ / M tokens | $0.15 | $7.50 |
| Results tracked | 4 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury 2.5 leads
Mercury 2.5: 39.5 (#156), Mistral Medium: 34.2 (#243)
| Benchmark | Mercury 2.5 | Mistral Medium |
|---|---|---|
| SciCode | 38.5% | 40.2% |
| ALE-Bench | 301.65 | 763.98 |
| FrontierCode | — | 8% |
| WeirdML | — | 43.7% |
| LMArena Coding | — | 1434 |
Agentic & Tool Use Not comparable
Mercury 2.5: —, Mistral Medium: 28.3 (#90)
| Benchmark | Mercury 2.5 | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
Reasoning Mistral Medium leads
Mercury 2.5: 22.4 (#193), Mistral Medium: 24.0 (#167)
| Benchmark | Mercury 2.5 | Mistral Medium |
|---|---|---|
| CritPt | 0% | 0% |
| Kagi LLM Benchmark | — | 50% |
| LMArena Hard Prompts | — | 1426 |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
Math Mistral Medium leads
Mercury 2.5: 23.3 (#272), Mistral Medium: 28.1 (#245)
| Benchmark | Mercury 2.5 | Mistral Medium |
|---|---|---|
| ProofBench | 3% | 9% |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| LMArena Math | — | 1408 |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Not comparable
Mercury 2.5: —, Mistral Medium: 25.0 (#265)
| Benchmark | Mercury 2.5 | Mistral Medium |
|---|---|---|
| GPQA Diamond | — | 59.5% |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |
| LMArena Expert | — | 1408 |
Multimodal Not comparable
Mercury 2.5: —, Mistral Medium: 35.3 (#88)
| Benchmark | Mercury 2.5 | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Not comparable
Mercury 2.5: —, Mistral Medium: 52.1 (#91)
| Benchmark | Mercury 2.5 | Mistral Medium |
|---|---|---|
| LMArena Non-English | — | 1408 |
| LMArena Chinese | — | 1447 |
| LMArena French | — | 1459 |
| LMArena German | — | 1432 |
| LMArena Japanese | — | 1378 |
| LMArena Korean | — | 1380 |
| LMArena Russian | — | 1411 |
| LMArena Spanish | — | 1433 |
Instruction Following Not comparable
Mercury 2.5: —, Mistral Medium: 73.7 (#116)
| Benchmark | Mercury 2.5 | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | — | 1398 |
Long Context Not comparable
Mercury 2.5: —, Mistral Medium: 42.9 (#114)
| Benchmark | Mercury 2.5 | Mistral Medium |
|---|---|---|
| LMArena Longer Query | — | 1406 |
Writing & Preference Not comparable
Mercury 2.5: —, Mistral Medium: 60.0 (#103)
| Benchmark | Mercury 2.5 | Mistral Medium |
|---|---|---|
| LMArena Text | — | 1424 |
| LMArena Creative Writing | — | 1391 |
| Short-Story Creative Writing | — | 77.3% |
| LMArena Multi-Turn | — | 1418 |
Frequently asked questions
Is Mercury 2.5 better than Mistral Medium?
Mistral Medium is the stronger model overall, scoring 36.3 to 33.5 on the Noometry Index. Mercury 2.5 costs 44× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Which is cheaper, Mercury 2.5 or Mistral Medium?
Mercury 2.5 is cheaper. It lists at $0.04 per million input tokens and $0.15 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Mercury 2.5 or Mistral Medium better for coding?
Mercury 2.5 scores higher on coding benchmarks: 39.5 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium does, with 262K tokens against 260K.
How many benchmarks do Mercury 2.5 and Mistral Medium share?
4 benchmarks have published results for both models. Mercury 2.5 has 4 scored results on Noometry and Mistral Medium has 36.