Model comparison
Codestral vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.1 to 30.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
Arcee AISummary
- The widest gap is in coding, where Trinity Large Thinking leads 33.8 to 26.9.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $0.30 / $0.90 for Codestral.
- Trinity Large Thinking accepts more context: 262K tokens versus 256K.
Side by side
| Codestral | Trinity Large Thinking | |
|---|---|---|
| Provider | Mistral AI | Arcee AI |
| Noometry Index | 30.1 | 38.1 |
| Released | 2024-05-29 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 256K | 262K |
| Max output | 4K | 80K |
| Input $ / M tokens | $0.30 | $0.25 |
| Output $ / M tokens | $0.90 | $0.80 |
| Results tracked | 7 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Trinity Large Thinking leads
Codestral: 26.9 (#316), Trinity Large Thinking: 33.8 (#238)
| Benchmark | Codestral | Trinity Large Thinking |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1381 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Codestral leads
Codestral: 19.1 (#244), Trinity Large Thinking: 16.3 (#298)
| Benchmark | Codestral | Trinity Large Thinking |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| LMArena Hard Prompts | — | 1350 |
| Surface Evolver Bench | — | 15.6% |
Math Not comparable
Codestral: —, Trinity Large Thinking: 34.9 (#149)
| Benchmark | Codestral | Trinity Large Thinking |
|---|---|---|
| LMArena Math | — | 1366 |
Knowledge Not comparable
Codestral: —, Trinity Large Thinking: 40.3 (#107)
| Benchmark | Codestral | Trinity Large Thinking |
|---|---|---|
| Vectara Hallucination Rate | — | 6.9% |
| LMArena Expert | — | 1359 |
Multilingual Not comparable
Codestral: —, Trinity Large Thinking: 46.4 (#155)
| Benchmark | Codestral | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | — | 1325 |
| LMArena Chinese | — | 1372 |
| LMArena French | — | 1374 |
| LMArena German | — | 1356 |
| LMArena Japanese | — | 1312 |
| LMArena Korean | — | 1304 |
| LMArena Russian | — | 1338 |
| LMArena Spanish | — | 1356 |
Instruction Following Not comparable
Codestral: —, Trinity Large Thinking: 70.7 (#157)
| Benchmark | Codestral | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | — | 1334 |
Long Context Not comparable
Codestral: —, Trinity Large Thinking: 41.2 (#139)
| Benchmark | Codestral | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | — | 1355 |
Writing & Preference Not comparable
Codestral: —, Trinity Large Thinking: 54.0 (#152)
| Benchmark | Codestral | Trinity Large Thinking |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1321 |
| LMArena Multi-Turn | — | 1342 |
Frequently asked questions
Is Codestral better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.1 to 30.1 on the Noometry Index.
Which is cheaper, Codestral 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; Codestral lists at $0.30 and $0.90.
Is Codestral or Trinity Large Thinking better for coding?
Trinity Large Thinking scores higher on coding benchmarks: 33.8 versus 26.9 in the Noometry coding category.
Which has the bigger context window?
Trinity Large Thinking does, with 262K tokens against 256K.
How many benchmarks do Codestral and Trinity Large Thinking share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Trinity Large Thinking has 24.