Model comparison
Mistral 7B vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 23.0 on the Noometry Index. Mistral 7B costs 1.6× less per token, which makes it the better buy when Trinity Large Thinking's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Mistral AI
Arcee AISummary
- They share 16 benchmarks with published results for both. Mistral 7B scores higher in 0 categories and Trinity Large Thinking in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Trinity Large Thinking leads 40.9 to 7.4.
- Mistral 7B is cheaper at $0.25 / $0.25 per million input/output tokens, against $0.25 / $0.80 for Trinity Large Thinking.
- Trinity Large Thinking accepts more context: 262K tokens versus 8K.
Side by side
| Mistral 7B | Trinity Large Thinking | |
|---|---|---|
| Provider | Mistral AI | Arcee AI |
| Noometry Index | 23.0 | 38.6 |
| Released | 2023-09-27 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 8K | 262K |
| Max output | 8K | 80K |
| Input $ / M tokens | $0.25 | $0.25 |
| Output $ / M tokens | $0.25 | $0.80 |
| Results tracked | 37 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Trinity Large Thinking leads
Mistral 7B: 26.4 (#326), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Mistral 7B | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1082 | 1381 |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| BigCodeBench Instruct | 19.5% | — |
| BigCodeBench Complete | 27.3% | — |
| HumanEval+ | 36% | — |
| MBPP+ | 42.1% | — |
Reasoning Trinity Large Thinking leads
Mistral 7B: 13.1 (#336), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Mistral 7B | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1067 | 1350 |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Chess Puzzles | 0% | — |
| Thematic Generalization | — | 41.6% |
| DTBench | 42.5% | — |
| Surface Evolver Bench | — | 15.6% |
| Adversarial NLI | 47.1% | — |
| BIG-Bench Hard | 56.1% | — |
| Epoch Capabilities Index | 112.21 | — |
| HellaSwag | 81% | — |
| PIQA | 83% | — |
| WinoGrande | 75.3% | — |
Math Trinity Large Thinking leads
Mistral 7B: 8.1 (#325), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Mistral 7B | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1085 | 1366 |
| OTIS Mock AIME 2024-2025 | 0.3% | — |
| MATH Level 5 | 3.7% | — |
| GSM8K | 54.4% | — |
Knowledge Trinity Large Thinking leads
Mistral 7B: 7.4 (#311), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Mistral 7B | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1036 | 1360 |
| GPQA Diamond | 15.2% | — |
| Vectara Hallucination Rate | — | 6.9% |
| ARC (AI2) Challenge | 78.6% | — |
| BoolQ | 87.4% | — |
| MMLU | 62.5% | — |
| OpenBookQA | 79.8% | — |
| TriviaQA | 75.2% | — |
Multilingual Trinity Large Thinking leads
Mistral 7B: 25.8 (#283), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Mistral 7B | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1012 | 1325 |
| LMArena Chinese | 1009 | 1373 |
| LMArena French | 1037 | 1374 |
| LMArena German | 987 | 1356 |
| LMArena Japanese | 878 | 1311 |
| LMArena Russian | 1018 | 1337 |
| LMArena Spanish | 1026 | 1357 |
| LMArena Korean | — | 1306 |
Instruction Following Trinity Large Thinking leads
Mistral 7B: 54.2 (#280), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Mistral 7B | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1060 | 1334 |
Long Context Trinity Large Thinking leads
Mistral 7B: 32.2 (#271), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Mistral 7B | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1060 | 1355 |
Writing & Preference Trinity Large Thinking leads
Mistral 7B: 30.7 (#286), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Mistral 7B | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1090 | 1340 |
| LMArena Creative Writing | 1068 | 1320 |
| LMArena Multi-Turn | 1062 | 1342 |
Frequently asked questions
Is Mistral 7B better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 23.0 on the Noometry Index. Mistral 7B costs 1.6× less per token, which makes it the better buy when Trinity Large Thinking's lead doesn't matter for your workload.
Which is cheaper, Mistral 7B or Trinity Large Thinking?
Mistral 7B is cheaper. It lists at $0.25 per million input tokens and $0.25 per million output tokens; Trinity Large Thinking lists at $0.25 and $0.80.
Is Mistral 7B or Trinity Large Thinking better for coding?
Trinity Large Thinking scores higher on coding benchmarks: 34.1 versus 26.4 in the Noometry coding category.
Which has the bigger context window?
Trinity Large Thinking does, with 262K tokens against 8K.
How many benchmarks do Mistral 7B and Trinity Large Thinking share?
16 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Trinity Large Thinking has 24.