Model comparison
GPT-5.4 mini vs Mixtral 8x22B
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 27.1 on the Noometry Index.
Last verified . 22 shared benchmarks.
Mistral AISummary
- They share 22 benchmarks with published results for both. GPT-5.4 mini scores higher in 9 categories and Mixtral 8x22B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 mini leads 51.5 to 15.1.
- The biggest single-benchmark swing is WeirdML: 60.3% for GPT-5.4 mini and 3.2% for Mixtral 8x22B.
- GPT-5.4 mini is cheaper at $0.75 / $4.50 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- GPT-5.4 mini accepts more context: 400K tokens versus 64K.
- Mixtral 8x22B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 mini | Mixtral 8x22B | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 45.0 | 27.1 |
| Released | 2026-03-17 | 2024-04-17 |
| Weights | Proprietary | Open |
| Context window | 400K | 64K |
| Max output | 128K | 64K |
| Input $ / M tokens | $0.75 | $2 |
| Output $ / M tokens | $4.50 | $6 |
| Results tracked | 46 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
GPT-5.4 mini: 45.2 (#72), Mixtral 8x22B: 24.2 (#329)
| Benchmark | GPT-5.4 mini | Mixtral 8x22B |
|---|---|---|
| WeirdML | 60.3% | 3.2% |
| LMArena Coding | 1438 | 1166 |
| FrontierCode | 27% | — |
| LMArena WebDev | 1397 | — |
| SciCode | 49.9% | — |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| ALE-Bench | 1,189 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use GPT-5.4 mini leads
GPT-5.4 mini: 29.9 (#81), Mixtral 8x22B: 23.1 (#127)
| Benchmark | GPT-5.4 mini | Mixtral 8x22B |
|---|---|---|
| Cybench | — | 7.5% |
| DeepResearch Bench | 36.3% | — |
Reasoning GPT-5.4 mini leads
GPT-5.4 mini: 30.4 (#85), Mixtral 8x22B: 19.9 (#248)
| Benchmark | GPT-5.4 mini | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1424 | 1150 |
| DTBench | 80% | 55.1% |
| Epoch Capabilities Index | 148.84 | 122.03 |
| ForecastBench | 57 | 56.3 |
| ARC-AGI-2 | 18.9% | — |
| Kagi LLM Benchmark | 37.9% | — |
| NYT Connections (extended) | 61.8% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 10% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 61.7% | — |
| Mystery Game Puzzles | 11% | — |
| LMCA | 40.8% | — |
Math GPT-5.4 mini leads
GPT-5.4 mini: 45.5 (#75), Mixtral 8x22B: 22.9 (#275)
| Benchmark | GPT-5.4 mini | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1419 | 1184 |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 9.8% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 21% | — |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |
| 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), Mixtral 8x22B: 15.1 (#293)
| Benchmark | GPT-5.4 mini | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | 86.9% | 34.1% |
| LMArena Expert | 1435 | 1113 |
| SimpleQA Verified | 29.4% | — |
| MMLU-Pro | — | 46% |
| Vectara Hallucination Rate | 5.5% | — |
| GPQA (HELM) | — | 33.4% |
| MMLU | — | 77.8% |
Multimodal Not comparable
GPT-5.4 mini: 39.7 (#56), Mixtral 8x22B: —
| Benchmark | GPT-5.4 mini | Mixtral 8x22B |
|---|---|---|
| LMArena Vision | 1245 | — |
Multilingual GPT-5.4 mini leads
GPT-5.4 mini: 51.9 (#96), Mixtral 8x22B: 32.8 (#255)
| Benchmark | GPT-5.4 mini | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1405 | 1128 |
| LMArena Chinese | 1446 | 1116 |
| LMArena French | 1440 | 1166 |
| LMArena German | 1409 | 1141 |
| LMArena Japanese | 1374 | 1037 |
| LMArena Korean | 1368 | 1057 |
| LMArena Russian | 1417 | 1158 |
| LMArena Spanish | 1405 | 1151 |
Instruction Following GPT-5.4 mini leads
GPT-5.4 mini: 74.1 (#102), Mixtral 8x22B: 57.7 (#266)
| Benchmark | GPT-5.4 mini | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1405 | 1147 |
| IFEval | — | 72.4% |
Long Context GPT-5.4 mini leads
GPT-5.4 mini: 43.0 (#112), Mixtral 8x22B: 34.7 (#247)
| Benchmark | GPT-5.4 mini | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1407 | 1144 |
Writing & Preference GPT-5.4 mini leads
GPT-5.4 mini: 64.0 (#58), Mixtral 8x22B: 36.9 (#262)
| Benchmark | GPT-5.4 mini | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1412 | 1162 |
| LMArena Creative Writing | 1370 | 1141 |
| LMArena Multi-Turn | 1429 | 1130 |
| EQ-Bench Creative Writing | 1665 | — |
| WildBench | — | 71.1% |
Frequently asked questions
Is GPT-5.4 mini better than Mixtral 8x22B?
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 27.1 on the Noometry Index.
Which is cheaper, GPT-5.4 mini or Mixtral 8x22B?
GPT-5.4 mini is cheaper. It lists at $0.75 per million input tokens and $4.50 per million output tokens; Mixtral 8x22B lists at $2 and $6.
Is GPT-5.4 mini or Mixtral 8x22B better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 24.2 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 mini does, with 400K tokens against 64K.
How many benchmarks do GPT-5.4 mini and Mixtral 8x22B share?
22 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Mixtral 8x22B has 34.