Model comparison
Mixtral 8x22B vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.1 to 26.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AI
Arcee AISummary
- They share 17 benchmarks with published results for both. Mixtral 8x22B scores higher in 1 category and Trinity Large Thinking in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Trinity Large Thinking leads 40.3 to 15.1.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- Trinity Large Thinking accepts more context: 262K tokens versus 64K.
Side by side
| Mixtral 8x22B | Trinity Large Thinking | |
|---|---|---|
| Provider | Mistral AI | Arcee AI |
| Noometry Index | 26.7 | 38.1 |
| Released | 2024-04-17 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 64K | 262K |
| Max output | 64K | 80K |
| Input $ / M tokens | $2 | $0.25 |
| Output $ / M tokens | $6 | $0.80 |
| Results tracked | 34 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Trinity Large Thinking leads
Mixtral 8x22B: 23.8 (#324), Trinity Large Thinking: 33.8 (#238)
| Benchmark | Mixtral 8x22B | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1166 | 1381 |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| WeirdML | 3.2% | — |
| BigCodeBench Instruct | 40.6% | — |
| BigCodeBench Complete | 50.2% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 64.3% | — |
Agentic & Tool Use Not comparable
Mixtral 8x22B: 22.8 (#119), Trinity Large Thinking: —
| Benchmark | Mixtral 8x22B | Trinity Large Thinking |
|---|---|---|
| Cybench | 7.5% | — |
Reasoning Mixtral 8x22B leads
Mixtral 8x22B: 19.1 (#246), Trinity Large Thinking: 16.3 (#298)
| Benchmark | Mixtral 8x22B | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1150 | 1350 |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| DTBench | 55.1% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 122 | — |
| ForecastBench | 56.3 | — |
Math Trinity Large Thinking leads
Mixtral 8x22B: 21.2 (#271), Trinity Large Thinking: 34.9 (#149)
| Benchmark | Mixtral 8x22B | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1184 | 1366 |
| Omni-MATH | 16.3% | — |
| MATH Level 5 | 24.2% | — |
Knowledge Trinity Large Thinking leads
Mixtral 8x22B: 15.1 (#288), Trinity Large Thinking: 40.3 (#107)
| Benchmark | Mixtral 8x22B | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1113 | 1359 |
| GPQA Diamond | 34.1% | — |
| MMLU-Pro | 46% | — |
| Vectara Hallucination Rate | — | 6.9% |
| GPQA (HELM) | 33.4% | — |
| MMLU | 77.8% | — |
Multilingual Trinity Large Thinking leads
Mixtral 8x22B: 32.9 (#250), Trinity Large Thinking: 46.4 (#155)
| Benchmark | Mixtral 8x22B | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1128 | 1325 |
| LMArena Chinese | 1116 | 1372 |
| LMArena French | 1165 | 1374 |
| LMArena German | 1141 | 1356 |
| LMArena Japanese | 1037 | 1312 |
| LMArena Korean | 1056 | 1304 |
| LMArena Russian | 1158 | 1338 |
| LMArena Spanish | 1150 | 1356 |
Instruction Following Trinity Large Thinking leads
Mixtral 8x22B: 57.9 (#261), Trinity Large Thinking: 70.7 (#157)
| Benchmark | Mixtral 8x22B | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1147 | 1334 |
| IFEval | 72.4% | — |
Long Context Trinity Large Thinking leads
Mixtral 8x22B: 34.6 (#242), Trinity Large Thinking: 41.2 (#139)
| Benchmark | Mixtral 8x22B | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1144 | 1355 |
Writing & Preference Trinity Large Thinking leads
Mixtral 8x22B: 37.1 (#257), Trinity Large Thinking: 54.0 (#152)
| Benchmark | Mixtral 8x22B | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1162 | 1340 |
| LMArena Creative Writing | 1141 | 1321 |
| LMArena Multi-Turn | 1130 | 1342 |
| WildBench | 71.1% | — |
Frequently asked questions
Is Mixtral 8x22B better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.1 to 26.7 on the Noometry Index.
Which is cheaper, Mixtral 8x22B or Trinity Large Thinking?
Trinity Large Thinking is cheaper. It lists at $0.25 per million input tokens and $0.80 per million output tokens; Mixtral 8x22B lists at $2 and $6.
Is Mixtral 8x22B or Trinity Large Thinking better for coding?
Trinity Large Thinking scores higher on coding benchmarks: 33.8 versus 23.8 in the Noometry coding category.
Which has the bigger context window?
Trinity Large Thinking does, with 262K tokens against 64K.
How many benchmarks do Mixtral 8x22B and Trinity Large Thinking share?
17 benchmarks have published results for both models. Mixtral 8x22B has 34 scored results on Noometry and Trinity Large Thinking has 24.