Model comparison
Devstral Small 2505 vs GPT-5.4 Pro
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 34.3 on the Noometry Index. Devstral Small 2505 costs 450× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
Mistral AISummary
- They share 1 benchmark with published results for both. Devstral Small 2505 scores higher in 0 categories and GPT-5.4 Pro in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 Pro leads 70.7 to 19.7.
- The biggest single-benchmark swing is CritPt: 0% for Devstral Small 2505 and 30% for GPT-5.4 Pro.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $30 / $180 for GPT-5.4 Pro.
- GPT-5.4 Pro accepts more context: 1.05M tokens versus 128K.
- Devstral Small 2505 has downloadable open weights; the other is API-only.
Side by side
| Devstral Small 2505 | GPT-5.4 Pro | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 34.3 | 58.9 |
| Released | 2025-05-07 | 2026-03-05 |
| Weights | Open | Proprietary |
| Context window | 128K | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $0.10 | $30 |
| Output $ / M tokens | $0.30 | $180 |
| Results tracked | 4 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 Pro leads
Devstral Small 2505: 38.9 (#166), GPT-5.4 Pro: 43.2 (#90)
| Benchmark | Devstral Small 2505 | GPT-5.4 Pro |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
| WeirdML | — | 57.4% |
Reasoning GPT-5.4 Pro leads
Devstral Small 2505: 19.7 (#252), GPT-5.4 Pro: 70.7 (#13)
| Benchmark | Devstral Small 2505 | GPT-5.4 Pro |
|---|---|---|
| CritPt | 0% | 30% |
| ARC-AGI-2 | — | 83.3% |
| SimpleBench | — | 74.1% |
| Kagi LLM Benchmark | 37.7% | — |
| ARC-AGI-1 | — | 94.5% |
| Chess Puzzles | — | 58.6% |
| EnigmaEval | — | 23.8% |
| Epoch Capabilities Index | — | 158.93 |
Math Not comparable
Devstral Small 2505: —, GPT-5.4 Pro: 72.4 (#22)
| Benchmark | Devstral Small 2505 | GPT-5.4 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 82.5% |
| FrontierMath Tier 4 | — | 58.5% |
| FrontierMath (Feb 2025 set) | — | 50% |
| FrontierMath Tier 4 (v1) | — | 37.5% |
Knowledge Not comparable
Devstral Small 2505: —, GPT-5.4 Pro: 68.3 (#7)
| Benchmark | Devstral Small 2505 | GPT-5.4 Pro |
|---|---|---|
| GPQA Diamond | — | 94.6% |
| Humanity's Last Exam | — | 44.3% |
| SimpleQA Verified | — | 46.3% |
| Vectara Hallucination Rate | — | 8.3% |
Frequently asked questions
Is Devstral Small 2505 better than GPT-5.4 Pro?
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 34.3 on the Noometry Index. Devstral Small 2505 costs 450× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.
Which is cheaper, Devstral Small 2505 or GPT-5.4 Pro?
Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; GPT-5.4 Pro lists at $30 and $180.
Is Devstral Small 2505 or GPT-5.4 Pro better for coding?
GPT-5.4 Pro scores higher on coding benchmarks: 43.2 versus 38.9 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 Pro does, with 1.05M tokens against 128K.
How many benchmarks do Devstral Small 2505 and GPT-5.4 Pro share?
1 benchmark has published results for both models. Devstral Small 2505 has 4 scored results on Noometry and GPT-5.4 Pro has 16.