Model comparison
Mercury 2 vs Mistral Small
Mercury 2 is the stronger model overall, scoring 38.8 to 33.1 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 Small in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mercury 2 leads 35.6 to 30.9.
- The biggest single-benchmark swing is SciCode: 38.7% for Mercury 2 and 26.5% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.25 / $0.75 for Mercury 2.
- Mistral Small accepts more context: 256K tokens versus 128K.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| Mercury 2 | Mistral Small | |
|---|---|---|
| Provider | Inception | Mistral AI |
| Noometry Index | 38.8 | 33.1 |
| Released | 2026-02-20 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 128K | 256K |
| Max output | 50K | 256K |
| Input $ / M tokens | $0.25 | $0.15 |
| Output $ / M tokens | $0.75 | $0.60 |
| Results tracked | 17 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mercury 2: 33.2 (#250), Mistral Small: 33.5 (#242)
| Benchmark | Mercury 2 | Mistral Small |
|---|---|---|
| SciCode | 38.7% | 26.5% |
| LMArena Coding | 1391 | 1363 |
| ALE-Bench | 785.58 | 497.62 |
| LMArena WebDev | 1170 | — |
| WeirdML | 43.2% | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
Agentic & Tool Use Not comparable
Mercury 2: —, Mistral Small: 27.9 (#87)
| Benchmark | Mercury 2 | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
Reasoning Mercury 2 leads
Mercury 2: 23.0 (#170), Mistral Small: 19.3 (#238)
| Benchmark | Mercury 2 | Mistral Small |
|---|---|---|
| CritPt | 0.8% | 0% |
| LMArena Hard Prompts | 1362 | 1336 |
| Kagi LLM Benchmark | — | 37.8% |
| LiveBench Reasoning | — | 44.8% |
| DTBench | — | 70.9% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| LiveBench | — | 44% |
Math Not comparable
Mercury 2: —, Mistral Small: 15.4 (#287)
| Benchmark | Mercury 2 | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| LiveBench Math | — | 39.9% |
| LMArena Math | — | 1341 |
| MATH Level 5 | — | 46.8% |
Knowledge Mercury 2 leads
Mercury 2: 35.6 (#170), Mistral Small: 30.9 (#214)
| Benchmark | Mercury 2 | Mistral Small |
|---|---|---|
| Vectara Hallucination Rate | 12.3% | 5.1% |
| LMArena Expert | 1358 | 1293 |
| GPQA Diamond | — | 47.5% |
| MMLU | — | 68.7% |
Multimodal Not comparable
Mercury 2: —, Mistral Small: 32.9 (#91)
| Benchmark | Mercury 2 | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual Mercury 2 leads
Mercury 2: 46.8 (#153), Mistral Small: 45.7 (#164)
| Benchmark | Mercury 2 | Mistral Small |
|---|---|---|
| LMArena Non-English | 1331 | 1315 |
| LMArena Chinese | 1416 | 1342 |
| LMArena Russian | 1303 | 1324 |
| LMArena French | — | 1337 |
| LMArena German | — | 1341 |
| LMArena Japanese | — | 1275 |
| LMArena Korean | — | 1260 |
| LMArena Spanish | — | 1346 |
Instruction Following Mercury 2 leads
Mercury 2: 70.4 (#161), Mistral Small: 66.6 (#204)
| Benchmark | Mercury 2 | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1328 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
Long Context Too close to call
Mercury 2: 40.4 (#149), Mistral Small: 40.4 (#151)
| Benchmark | Mercury 2 | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1329 | 1327 |
Writing & Preference Mercury 2 leads
Mercury 2: 54.0 (#151), Mistral Small: 52.6 (#165)
| Benchmark | Mercury 2 | Mistral Small |
|---|---|---|
| LMArena Text | 1355 | 1338 |
| LMArena Creative Writing | 1289 | 1304 |
| LMArena Multi-Turn | 1358 | 1344 |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is Mercury 2 better than Mistral Small?
Mercury 2 is the stronger model overall, scoring 38.8 to 33.1 on the Noometry Index.
Which is cheaper, Mercury 2 or Mistral Small?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Mercury 2 lists at $0.25 and $0.75.
Is Mercury 2 or Mistral Small better for coding?
They score almost the same on coding (33.2 vs 33.5); test both on your own repository before choosing.
Which has the bigger context window?
Mistral Small does, with 256K tokens against 128K.
How many benchmarks do Mercury 2 and Mistral Small share?
15 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Mistral Small has 39.