Model comparison
Mistral Large 4 vs Pixtral Large
Mistral Large 4 is the stronger model overall, scoring 43.1 to 32.2 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AISummary
- The widest gap is in writing & preference, where Mistral Large 4 leads 60.4 to 32.9.
- Mistral Large 4 is cheaper at $0.68 / $2.09 per million input/output tokens, against $2 / $6 for Pixtral Large.
- Mistral Large 4 accepts more context: 1.05M tokens versus 128K.
- Pixtral Large has downloadable open weights; the other is API-only.
Side by side
| Mistral Large 4 | Pixtral Large | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 43.1 | 32.2 |
| Released | 2026-10-06 | 2024-11-01 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 128K |
| Max output | 262K | 128K |
| Input $ / M tokens | $0.68 | $2 |
| Output $ / M tokens | $2.09 | $6 |
| Results tracked | 15 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mistral Large 4: 48.6 (#57), Pixtral Large: —
| Benchmark | Mistral Large 4 | Pixtral Large |
|---|---|---|
| LMArena WebDev | 1541 | — |
| LMArena Coding | 1475 | — |
Reasoning Too close to call
Mistral Large 4: 22.5 (#192), Pixtral Large: 21.7 (#218)
| Benchmark | Mistral Large 4 | Pixtral Large |
|---|---|---|
| NYT Connections (extended) | 27.4% | — |
| EnigmaEval | — | 0.8% |
| LMArena Hard Prompts | 1444 | — |
Math Not comparable
Mistral Large 4: 40.4 (#91), Pixtral Large: —
| Benchmark | Mistral Large 4 | Pixtral Large |
|---|---|---|
| LMArena Math | 1488 | — |
Knowledge Not comparable
Mistral Large 4: 36.6 (#166), Pixtral Large: —
| Benchmark | Mistral Large 4 | Pixtral Large |
|---|---|---|
| SimpleQA Verified | 20% | — |
| LMArena Expert | 1447 | — |
Multimodal Not comparable
Mistral Large 4: —, Pixtral Large: 30.6 (#111)
| Benchmark | Mistral Large 4 | Pixtral Large |
|---|---|---|
| LMArena Vision | — | 1089 |
Multilingual Not comparable
Mistral Large 4: 52.6 (#82), Pixtral Large: —
| Benchmark | Mistral Large 4 | Pixtral Large |
|---|---|---|
| LMArena Non-English | 1415 | — |
| LMArena Chinese | 1491 | — |
| LMArena Russian | 1414 | — |
Instruction Following Not comparable
Mistral Large 4: 75.0 (#76), Pixtral Large: —
| Benchmark | Mistral Large 4 | Pixtral Large |
|---|---|---|
| LMArena Instruction Following | 1424 | — |
Long Context Not comparable
Mistral Large 4: 43.6 (#89), Pixtral Large: —
| Benchmark | Mistral Large 4 | Pixtral Large |
|---|---|---|
| LMArena Longer Query | 1429 | — |
Writing & Preference Mistral Large 4 leads
Mistral Large 4: 60.4 (#97), Pixtral Large: 32.9 (#278)
| Benchmark | Mistral Large 4 | Pixtral Large |
|---|---|---|
| LMArena Text | 1427 | — |
| LMArena Creative Writing | 1361 | — |
| EQ-Bench Creative Writing | — | 988 |
| LMArena Multi-Turn | 1424 | — |
Frequently asked questions
Is Mistral Large 4 better than Pixtral Large?
Mistral Large 4 is the stronger model overall, scoring 43.1 to 32.2 on the Noometry Index.
Which is cheaper, Mistral Large 4 or Pixtral Large?
Mistral Large 4 is cheaper. It lists at $0.68 per million input tokens and $2.09 per million output tokens; Pixtral Large lists at $2 and $6.
Which has the bigger context window?
Mistral Large 4 does, with 1.05M tokens against 128K.
How many benchmarks do Mistral Large 4 and Pixtral Large share?
0 benchmarks have published results for both models. Mistral Large 4 has 15 scored results on Noometry and Pixtral Large has 3.