Model comparison
GPT-5.6 Terra vs Mixtral 8x22B
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 27.1 on the Noometry Index. Mixtral 8x22B costs 1.5× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Mistral AISummary
- They share 21 benchmarks with published results for both. GPT-5.6 Terra scores higher in 9 categories and Mixtral 8x22B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Terra leads 81.6 to 22.9.
- The biggest single-benchmark swing is WeirdML: 78.3% for GPT-5.6 Terra and 3.2% for Mixtral 8x22B.
- Mixtral 8x22B is cheaper at $2 / $6 per million input/output tokens, against $2 / $12 for GPT-5.6 Terra.
- GPT-5.6 Terra accepts more context: 1.05M tokens versus 64K.
- Mixtral 8x22B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.6 Terra | Mixtral 8x22B | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 59.2 | 27.1 |
| Released | 2026-07-09 | 2024-04-17 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 64K |
| Max output | 128K | 64K |
| Input $ / M tokens | $2 | $2 |
| Output $ / M tokens | $12 | $6 |
| Results tracked | 52 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Terra leads
GPT-5.6 Terra: 57.7 (#19), Mixtral 8x22B: 24.2 (#329)
| Benchmark | GPT-5.6 Terra | Mixtral 8x22B |
|---|---|---|
| WeirdML | 78.3% | 3.2% |
| LMArena Coding | 1484 | 1166 |
| DeepSWE | 69.6% | — |
| FrontierCode | 41.3% | — |
| CursorBench | 41.3% | — |
| LMArena WebDev | 1522 | — |
| SciCode | 55% | — |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| ALE-Bench | 1,951 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use GPT-5.6 Terra leads
GPT-5.6 Terra: 40.1 (#25), Mixtral 8x22B: 23.1 (#127)
| Benchmark | GPT-5.6 Terra | Mixtral 8x22B |
|---|---|---|
| APEX-Agents | 58.2% | — |
| Cybench | — | 7.5% |
| BALROG | 53.2% | — |
| GDP.pdf | 24.7% | — |
| Vending-Bench 2 | 7,343 | — |
Reasoning GPT-5.6 Terra leads
GPT-5.6 Terra: 60.7 (#21), Mixtral 8x22B: 19.9 (#248)
| Benchmark | GPT-5.6 Terra | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1468 | 1150 |
| DTBench | 93.3% | 55.1% |
| Epoch Capabilities Index | 159.62 | 122.03 |
| ARC-AGI-2 | 83.9% | — |
| SimpleBench | 48.9% | — |
| Kagi LLM Benchmark | 51.3% | — |
| NYT Connections (extended) | 78.4% | — |
| ARC-AGI-1 | 96.5% | — |
| CritPt | 30% | — |
| Chess Puzzles | 54% | — |
| Mystery Game Puzzles | 35% | — |
| LMCA | 55% | — |
| Surface Evolver Bench | 83.8% | — |
| ForecastBench | — | 56.3 |
Math GPT-5.6 Terra leads
GPT-5.6 Terra: 81.6 (#12), Mixtral 8x22B: 22.9 (#275)
| Benchmark | GPT-5.6 Terra | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1466 | 1184 |
| FrontierMath (Tiers 1-3) | 86% | — |
| FrontierMath Tier 4 | 70.7% | — |
| OTIS Mock AIME 2024-2025 | 99.7% | — |
| ProofBench | 74% | — |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |
Knowledge GPT-5.6 Terra leads
GPT-5.6 Terra: 61.2 (#30), Mixtral 8x22B: 15.1 (#293)
| Benchmark | GPT-5.6 Terra | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | 93.3% | 34.1% |
| LMArena Expert | 1492 | 1113 |
| SimpleQA Verified | 43.2% | — |
| MMLU-Pro | — | 46% |
| GPQA (HELM) | — | 33.4% |
| MMLU | — | 77.8% |
Multimodal Not comparable
GPT-5.6 Terra: 47.3 (#11), Mixtral 8x22B: —
| Benchmark | GPT-5.6 Terra | Mixtral 8x22B |
|---|---|---|
| LMArena Vision | 1271 | — |
| Blueprint-Bench 2 | 30.8% | — |
| Furniture Assembly | 54.2% | — |
| LMArena Document | 1472 | — |
Multilingual GPT-5.6 Terra leads
GPT-5.6 Terra: 54.4 (#44), Mixtral 8x22B: 32.8 (#255)
| Benchmark | GPT-5.6 Terra | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1439 | 1128 |
| LMArena Chinese | 1513 | 1116 |
| LMArena French | 1471 | 1166 |
| LMArena German | 1460 | 1141 |
| LMArena Japanese | 1457 | 1037 |
| LMArena Korean | 1425 | 1057 |
| LMArena Russian | 1450 | 1158 |
| LMArena Spanish | 1448 | 1151 |
Instruction Following GPT-5.6 Terra leads
GPT-5.6 Terra: 76.4 (#40), Mixtral 8x22B: 57.7 (#266)
| Benchmark | GPT-5.6 Terra | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1454 | 1147 |
| IFEval | — | 72.4% |
Long Context GPT-5.6 Terra leads
GPT-5.6 Terra: 44.4 (#68), Mixtral 8x22B: 34.7 (#247)
| Benchmark | GPT-5.6 Terra | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1451 | 1144 |
Writing & Preference GPT-5.6 Terra leads
GPT-5.6 Terra: 70.2 (#23), Mixtral 8x22B: 36.9 (#262)
| Benchmark | GPT-5.6 Terra | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1447 | 1162 |
| LMArena Creative Writing | 1410 | 1141 |
| LMArena Multi-Turn | 1449 | 1130 |
| EQ-Bench Creative Writing | 1855 | — |
| WildBench | — | 71.1% |
| EQ-Bench 4 | 1234 | — |
Frequently asked questions
Is GPT-5.6 Terra better than Mixtral 8x22B?
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 27.1 on the Noometry Index. Mixtral 8x22B costs 1.5× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.
Which is cheaper, GPT-5.6 Terra or Mixtral 8x22B?
Mixtral 8x22B is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; GPT-5.6 Terra lists at $2 and $12.
Is GPT-5.6 Terra or Mixtral 8x22B better for coding?
GPT-5.6 Terra scores higher on coding benchmarks: 57.7 versus 24.2 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Terra does, with 1.05M tokens against 64K.
How many benchmarks do GPT-5.6 Terra and Mixtral 8x22B share?
21 benchmarks have published results for both models. GPT-5.6 Terra has 52 scored results on Noometry and Mixtral 8x22B has 34.