Model comparison
GPT-5.4 mini vs Mistral Large 4
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 43.1 on the Noometry Index. Mistral Large 4 costs 1.6× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
Mistral AISummary
- They share 15 benchmarks with published results for both. GPT-5.4 mini scores higher in 4 categories and Mistral Large 4 in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 mini leads 51.5 to 36.6.
- The biggest single-benchmark swing is NYT Connections (extended): 61.8% for GPT-5.4 mini and 27.4% for Mistral Large 4.
- Mistral Large 4 is cheaper at $0.68 / $2.09 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- Mistral Large 4 accepts more context: 1.05M tokens versus 400K.
Side by side
| GPT-5.4 mini | Mistral Large 4 | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 45.0 | 43.1 |
| Released | 2026-03-17 | 2026-10-06 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1.05M |
| Max output | 128K | 262K |
| Input $ / M tokens | $0.75 | $0.68 |
| Output $ / M tokens | $4.50 | $2.09 |
| Results tracked | 46 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 4 leads
GPT-5.4 mini: 45.2 (#72), Mistral Large 4: 48.6 (#57)
| Benchmark | GPT-5.4 mini | Mistral Large 4 |
|---|---|---|
| LMArena WebDev | 1397 | 1541 |
| LMArena Coding | 1438 | 1475 |
| FrontierCode | 27% | — |
| SciCode | 49.9% | — |
| WeirdML | 60.3% | — |
| ALE-Bench | 1,189 | — |
Agentic & Tool Use Not comparable
GPT-5.4 mini: 29.9 (#81), Mistral Large 4: —
| Benchmark | GPT-5.4 mini | Mistral Large 4 |
|---|---|---|
| DeepResearch Bench | 36.3% | — |
Reasoning GPT-5.4 mini leads
GPT-5.4 mini: 30.4 (#85), Mistral Large 4: 22.5 (#192)
| Benchmark | GPT-5.4 mini | Mistral Large 4 |
|---|---|---|
| NYT Connections (extended) | 61.8% | 27.4% |
| LMArena Hard Prompts | 1424 | 1444 |
| ARC-AGI-2 | 18.9% | — |
| Kagi LLM Benchmark | 37.9% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 10% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 61.7% | — |
| Mystery Game Puzzles | 11% | — |
| DTBench | 80% | — |
| LMCA | 40.8% | — |
| Epoch Capabilities Index | 148.84 | — |
| ForecastBench | 57 | — |
Math GPT-5.4 mini leads
GPT-5.4 mini: 45.5 (#75), Mistral Large 4: 40.4 (#91)
| Benchmark | GPT-5.4 mini | Mistral Large 4 |
|---|---|---|
| LMArena Math | 1419 | 1488 |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 9.8% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 21% | — |
| FrontierMath (Feb 2025 set) | 28.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GPT-5.4 mini leads
GPT-5.4 mini: 51.5 (#67), Mistral Large 4: 36.6 (#166)
| Benchmark | GPT-5.4 mini | Mistral Large 4 |
|---|---|---|
| SimpleQA Verified | 29.4% | 20% |
| LMArena Expert | 1435 | 1447 |
| GPQA Diamond | 86.9% | — |
| Vectara Hallucination Rate | 5.5% | — |
Multimodal Not comparable
GPT-5.4 mini: 39.7 (#56), Mistral Large 4: —
| Benchmark | GPT-5.4 mini | Mistral Large 4 |
|---|---|---|
| LMArena Vision | 1245 | — |
Multilingual Too close to call
GPT-5.4 mini: 51.9 (#96), Mistral Large 4: 52.6 (#82)
| Benchmark | GPT-5.4 mini | Mistral Large 4 |
|---|---|---|
| LMArena Non-English | 1405 | 1415 |
| LMArena Chinese | 1446 | 1491 |
| LMArena Russian | 1417 | 1414 |
| LMArena French | 1440 | — |
| LMArena German | 1409 | — |
| LMArena Japanese | 1374 | — |
| LMArena Korean | 1368 | — |
| LMArena Spanish | 1405 | — |
Instruction Following Too close to call
GPT-5.4 mini: 74.1 (#102), Mistral Large 4: 75.0 (#76)
| Benchmark | GPT-5.4 mini | Mistral Large 4 |
|---|---|---|
| LMArena Instruction Following | 1405 | 1424 |
Long Context Too close to call
GPT-5.4 mini: 43.0 (#112), Mistral Large 4: 43.6 (#89)
| Benchmark | GPT-5.4 mini | Mistral Large 4 |
|---|---|---|
| LMArena Longer Query | 1407 | 1429 |
Writing & Preference GPT-5.4 mini leads
GPT-5.4 mini: 64.0 (#58), Mistral Large 4: 60.4 (#97)
| Benchmark | GPT-5.4 mini | Mistral Large 4 |
|---|---|---|
| LMArena Text | 1412 | 1427 |
| LMArena Creative Writing | 1370 | 1361 |
| LMArena Multi-Turn | 1429 | 1424 |
| EQ-Bench Creative Writing | 1665 | — |
Frequently asked questions
Is GPT-5.4 mini better than Mistral Large 4?
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 43.1 on the Noometry Index. Mistral Large 4 costs 1.6× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.
Which is cheaper, GPT-5.4 mini or Mistral Large 4?
Mistral Large 4 is cheaper. It lists at $0.68 per million input tokens and $2.09 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.
Is GPT-5.4 mini or Mistral Large 4 better for coding?
Mistral Large 4 scores higher on coding benchmarks: 48.6 versus 45.2 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 4 does, with 1.05M tokens against 400K.
How many benchmarks do GPT-5.4 mini and Mistral Large 4 share?
15 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Mistral Large 4 has 15.