Model comparison
Ministral 8B vs Pixtral Large
Pixtral Large is the stronger model overall, scoring 31.7 to 27.8 on the Noometry Index. Ministral 8B costs 30× less per token, which makes it the better buy when Pixtral Large's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Mistral AISummary
- The widest gap is in writing & preference, where Ministral 8B leads 39.8 to 32.9.
- Ministral 8B is cheaper at $0.10 / $0.10 per million input/output tokens, against $2 / $6 for Pixtral Large.
Side by side
| Ministral 8B | Pixtral Large | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 27.8 | 31.7 |
| Released | 2024-10-01 | 2024-11-01 |
| Weights | Open | Open |
| Context window | 128K | 128K |
| Max output | 128K | 128K |
| Input $ / M tokens | $0.10 | $2 |
| Output $ / M tokens | $0.10 | $6 |
| Results tracked | 17 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Ministral 8B: 34.4 (#226), Pixtral Large: —
| Benchmark | Ministral 8B | Pixtral Large |
|---|---|---|
| LMArena Coding | 1202 | — |
Agentic & Tool Use Not comparable
Ministral 8B: 16.2 (#140), Pixtral Large: —
| Benchmark | Ministral 8B | Pixtral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | 11.1% | — |
Reasoning Pixtral Large leads
Ministral 8B: 17.7 (#279), Pixtral Large: 20.9 (#208)
| Benchmark | Ministral 8B | Pixtral Large |
|---|---|---|
| EnigmaEval | — | 0.8% |
| LMArena Hard Prompts | 1191 | — |
| DTBench | 45.7% | — |
Math Not comparable
Ministral 8B: 23.7 (#262), Pixtral Large: —
| Benchmark | Ministral 8B | Pixtral Large |
|---|---|---|
| LMArena Math | 1188 | — |
| MATH Level 5 | 14.9% | — |
Knowledge Not comparable
Ministral 8B: 12.5 (#292), Pixtral Large: —
| Benchmark | Ministral 8B | Pixtral Large |
|---|---|---|
| GPQA Diamond | 27.1% | — |
| Vectara Hallucination Rate | 7.4% | — |
| LMArena Expert | 1170 | — |
Multimodal Not comparable
Ministral 8B: —, Pixtral Large: 30.0 (#105)
| Benchmark | Ministral 8B | Pixtral Large |
|---|---|---|
| LMArena Vision | — | 1089 |
Multilingual Not comparable
Ministral 8B: 35.3 (#242), Pixtral Large: —
| Benchmark | Ministral 8B | Pixtral Large |
|---|---|---|
| LMArena Non-English | 1165 | — |
| LMArena Chinese | 1193 | — |
| LMArena Russian | 1195 | — |
Instruction Following Not comparable
Ministral 8B: 60.7 (#245), Pixtral Large: —
| Benchmark | Ministral 8B | Pixtral Large |
|---|---|---|
| LMArena Instruction Following | 1161 | — |
Long Context Not comparable
Ministral 8B: 36.7 (#222), Pixtral Large: —
| Benchmark | Ministral 8B | Pixtral Large |
|---|---|---|
| LMArena Longer Query | 1212 | — |
Writing & Preference Ministral 8B leads
Ministral 8B: 39.8 (#241), Pixtral Large: 32.9 (#273)
| Benchmark | Ministral 8B | Pixtral Large |
|---|---|---|
| LMArena Text | 1191 | — |
| LMArena Creative Writing | 1175 | — |
| EQ-Bench Creative Writing | — | 988 |
| LMArena Multi-Turn | 1166 | — |
Frequently asked questions
Is Ministral 8B better than Pixtral Large?
Pixtral Large is the stronger model overall, scoring 31.7 to 27.8 on the Noometry Index. Ministral 8B costs 30× less per token, which makes it the better buy when Pixtral Large's lead doesn't matter for your workload.
Which is cheaper, Ministral 8B or Pixtral Large?
Ministral 8B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; Pixtral Large lists at $2 and $6.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do Ministral 8B and Pixtral Large share?
0 benchmarks have published results for both models. Ministral 8B has 17 scored results on Noometry and Pixtral Large has 3.