Model comparison
Chatgpt 4o Latest 20250326 vs Devstral Small 2505
Chatgpt 4o Latest 20250326 is the stronger model overall, scoring 43.8 to 34.3 on the Noometry Index.
Last verified . 1 shared benchmarks.
Mistral AISummary
- They share 1 benchmark with published results for both. Chatgpt 4o Latest 20250326 scores higher in 2 categories and Devstral Small 2505 in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Chatgpt 4o Latest 20250326 leads 33.8 to 19.7.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 75% for Chatgpt 4o Latest 20250326 and 37.7% for Devstral Small 2505.
- Devstral Small 2505 has downloadable open weights; the other is API-only.
Side by side
| Chatgpt 4o Latest 20250326 | Devstral Small 2505 | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 43.8 | 34.3 |
| Released | — | 2025-05-07 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 21 | 4 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 41.6 (#122), Devstral Small 2505: 38.9 (#166)
| Benchmark | Chatgpt 4o Latest 20250326 | Devstral Small 2505 |
|---|---|---|
| SWE-bench Verified (bash only) | — | 56.4% |
| SciCode | — | 28.8% |
| LMArena Coding | 1413 | — |
Reasoning Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 33.8 (#71), Devstral Small 2505: 19.7 (#252)
| Benchmark | Chatgpt 4o Latest 20250326 | Devstral Small 2505 |
|---|---|---|
| Kagi LLM Benchmark | 75% | 37.7% |
| CritPt | — | 0% |
| LMArena Hard Prompts | 1424 | — |
Math Not comparable
Chatgpt 4o Latest 20250326: 38.6 (#134), Devstral Small 2505: —
| Benchmark | Chatgpt 4o Latest 20250326 | Devstral Small 2505 |
|---|---|---|
| LMArena Math | 1407 | — |
Knowledge Not comparable
Chatgpt 4o Latest 20250326: 39.2 (#137), Devstral Small 2505: —
| Benchmark | Chatgpt 4o Latest 20250326 | Devstral Small 2505 |
|---|---|---|
| Confabulations | 16.6% | — |
| LMArena Expert | 1401 | — |
Multimodal Not comparable
Chatgpt 4o Latest 20250326: 39.6 (#58), Devstral Small 2505: —
| Benchmark | Chatgpt 4o Latest 20250326 | Devstral Small 2505 |
|---|---|---|
| LMArena Vision | 1243 | — |
Multilingual Not comparable
Chatgpt 4o Latest 20250326: 52.9 (#76), Devstral Small 2505: —
| Benchmark | Chatgpt 4o Latest 20250326 | Devstral Small 2505 |
|---|---|---|
| LMArena Non-English | 1419 | — |
| LMArena Chinese | 1457 | — |
| LMArena French | 1446 | — |
| LMArena German | 1423 | — |
| LMArena Japanese | 1405 | — |
| LMArena Korean | 1396 | — |
| LMArena Russian | 1429 | — |
| LMArena Spanish | 1434 | — |
Instruction Following Not comparable
Chatgpt 4o Latest 20250326: 74.0 (#107), Devstral Small 2505: —
| Benchmark | Chatgpt 4o Latest 20250326 | Devstral Small 2505 |
|---|---|---|
| LMArena Instruction Following | 1403 | — |
Long Context Not comparable
Chatgpt 4o Latest 20250326: 43.1 (#107), Devstral Small 2505: —
| Benchmark | Chatgpt 4o Latest 20250326 | Devstral Small 2505 |
|---|---|---|
| LMArena Longer Query | 1413 | — |
Writing & Preference Not comparable
Chatgpt 4o Latest 20250326: 62.6 (#72), Devstral Small 2505: —
| Benchmark | Chatgpt 4o Latest 20250326 | Devstral Small 2505 |
|---|---|---|
| LMArena Text | 1429 | — |
| LMArena Creative Writing | 1405 | — |
| EQ-Bench Creative Writing | 1501 | — |
| LMArena Multi-Turn | 1454 | — |
Frequently asked questions
Is Chatgpt 4o Latest 20250326 better than Devstral Small 2505?
Chatgpt 4o Latest 20250326 is the stronger model overall, scoring 43.8 to 34.3 on the Noometry Index.
Is Chatgpt 4o Latest 20250326 or Devstral Small 2505 better for coding?
Chatgpt 4o Latest 20250326 scores higher on coding benchmarks: 41.6 versus 38.9 in the Noometry coding category.
How many benchmarks do Chatgpt 4o Latest 20250326 and Devstral Small 2505 share?
1 benchmark has published results for both models. Chatgpt 4o Latest 20250326 has 21 scored results on Noometry and Devstral Small 2505 has 4.