Model comparison
Mistral Small 3 vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 31.2 on the Noometry Index. Mistral Small 3 costs 6.7× 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 Small 3 scores higher in 2 categories and Trinity Large Thinking in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Trinity Large Thinking leads 53.8 to 32.2.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.25 / $0.80 for Trinity Large Thinking.
- Trinity Large Thinking accepts more context: 262K tokens versus 33K.
Side by side
| Mistral Small 3 | Trinity Large Thinking | |
|---|---|---|
| Provider | Mistral AI | Arcee AI |
| Noometry Index | 31.2 | 38.6 |
| Released | 2025-01-30 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 33K | 262K |
| Max output | 16K | 80K |
| Input $ / M tokens | $0.05 | $0.25 |
| Output $ / M tokens | $0.08 | $0.80 |
| Results tracked | 24 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3 leads
Mistral Small 3: 36.5 (#207), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Mistral Small 3 | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1246 | 1381 |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| BigCodeBench Instruct | 45.3% | — |
| BigCodeBench Complete | 50.4% | — |
Reasoning Mistral Small 3 leads
Mistral Small 3: 18.9 (#273), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Mistral Small 3 | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1233 | 1350 |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Chess Puzzles | 0% | — |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 127.07 | — |
Math Trinity Large Thinking leads
Mistral Small 3: 16.3 (#295), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Mistral Small 3 | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1240 | 1366 |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
Knowledge Trinity Large Thinking leads
Mistral Small 3: 25.1 (#263), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Mistral Small 3 | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1202 | 1360 |
| GPQA Diamond | 47.3% | — |
| Confabulations | 25.2% | — |
| Vectara Hallucination Rate | — | 6.9% |
Multilingual Trinity Large Thinking leads
Mistral Small 3: 37.3 (#236), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Mistral Small 3 | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1198 | 1325 |
| LMArena Chinese | 1204 | 1373 |
| LMArena French | 1203 | 1374 |
| LMArena German | 1211 | 1356 |
| LMArena Japanese | 1111 | 1311 |
| LMArena Korean | 1188 | 1306 |
| LMArena Russian | 1216 | 1337 |
| LMArena Spanish | — | 1357 |
Instruction Following Trinity Large Thinking leads
Mistral Small 3: 63.7 (#229), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Mistral Small 3 | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1214 | 1334 |
Long Context Trinity Large Thinking leads
Mistral Small 3: 37.8 (#211), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Mistral Small 3 | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1246 | 1355 |
Writing & Preference Trinity Large Thinking leads
Mistral Small 3: 32.2 (#280), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Mistral Small 3 | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1234 | 1340 |
| LMArena Creative Writing | 1195 | 1320 |
| LMArena Multi-Turn | 1217 | 1342 |
| EQ-Bench Creative Writing | 707 | — |
Frequently asked questions
Is Mistral Small 3 better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 31.2 on the Noometry Index. Mistral Small 3 costs 6.7× 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 Small 3 or Trinity Large Thinking?
Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Trinity Large Thinking lists at $0.25 and $0.80.
Is Mistral Small 3 or Trinity Large Thinking better for coding?
Mistral Small 3 scores higher on coding benchmarks: 36.5 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Trinity Large Thinking does, with 262K tokens against 33K.
How many benchmarks do Mistral Small 3 and Trinity Large Thinking share?
16 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Trinity Large Thinking has 24.