Model comparison
Devstral Small 2505 vs Mercury
Mercury is the stronger model overall, scoring 37.6 to 34.3 on the Noometry Index.
Last verified . 1 shared benchmarks.
Mistral AISummary
- They share 1 benchmark with published results for both. Devstral Small 2505 scores higher in 2 categories and Mercury in 0 categories; one gap is clear of the uncertainty.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 37.7% for Devstral Small 2505 and 21.6% for Mercury.
- Devstral Small 2505 has downloadable open weights; the other is API-only.
Side by side
| Devstral Small 2505 | Mercury | |
|---|---|---|
| Provider | Mistral AI | Inception |
| Noometry Index | 34.3 | 37.6 |
| Released | 2025-05-07 | — |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 4 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Devstral Small 2505: 38.9 (#166), Mercury: 38.7 (#170)
| Benchmark | Devstral Small 2505 | Mercury |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
| LMArena Coding | — | 1322 |
Reasoning Devstral Small 2505 leads
Devstral Small 2505: 19.7 (#252), Mercury: 17.5 (#293)
| Benchmark | Devstral Small 2505 | Mercury |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | 21.6% |
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1285 |
Multilingual Not comparable
Devstral Small 2505: —, Mercury: 41.6 (#206)
| Benchmark | Devstral Small 2505 | Mercury |
|---|---|---|
| LMArena Non-English | — | 1260 |
Instruction Following Not comparable
Devstral Small 2505: —, Mercury: 65.2 (#224)
| Benchmark | Devstral Small 2505 | Mercury |
|---|---|---|
| LMArena Instruction Following | — | 1239 |
Long Context Not comparable
Devstral Small 2505: —, Mercury: 38.4 (#198)
| Benchmark | Devstral Small 2505 | Mercury |
|---|---|---|
| LMArena Longer Query | — | 1266 |
Writing & Preference Not comparable
Devstral Small 2505: —, Mercury: 46.2 (#221)
| Benchmark | Devstral Small 2505 | Mercury |
|---|---|---|
| LMArena Text | — | 1282 |
| LMArena Creative Writing | — | 1191 |
| LMArena Multi-Turn | — | 1282 |
Frequently asked questions
Is Devstral Small 2505 better than Mercury?
Mercury is the stronger model overall, scoring 37.6 to 34.3 on the Noometry Index.
Is Devstral Small 2505 or Mercury better for coding?
They score almost the same on coding (38.9 vs 38.7); test both on your own repository before choosing.
How many benchmarks do Devstral Small 2505 and Mercury share?
1 benchmark has published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Mercury has 9.