Model comparison
Inkling-Small vs Mistral Small 3.1
Inkling-Small is the stronger model overall, scoring 46.5 to 31.7 on the Noometry Index. Mistral Small 3.1 costs 1.6× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
Mistral AISummary
- They share 23 benchmarks with published results for both. Inkling-Small scores higher in 9 categories and Mistral Small 3.1 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Inkling-Small leads 45.1 to 14.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 90% for Inkling-Small and 3.9% for Mistral Small 3.1.
- Mistral Small 3.1 is cheaper at $0.35 / $0.56 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Inkling-Small accepts more context: 524K tokens versus 128K.
Side by side
| Inkling-Small | Mistral Small 3.1 | |
|---|---|---|
| Provider | Thinking Machines Lab | Mistral AI |
| Noometry Index | 46.5 | 31.7 |
| Released | 2026-07-15 | 2025-03-17 |
| Weights | Open | Open |
| Context window | 524K | 128K |
| Max output | 1.05M | 102K |
| Input $ / M tokens | $0.45 | $0.35 |
| Output $ / M tokens | $1.20 | $0.56 |
| Results tracked | 33 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Inkling-Small: 43.6 (#85), Mistral Small 3.1: 38.3 (#179)
| Benchmark | Inkling-Small | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1451 | 1309 |
| LMArena WebDev | 1409 | — |
| SciCode | 48.7% | — |
Reasoning Inkling-Small leads
Inkling-Small: 38.6 (#63), Mistral Small 3.1: 19.7 (#254)
| Benchmark | Inkling-Small | Mistral Small 3.1 |
|---|---|---|
| Chess Puzzles | 18% | 1% |
| LMArena Hard Prompts | 1423 | 1278 |
| Epoch Capabilities Index | 150.15 | 127.48 |
| ARC-AGI-2 | 40.1% | — |
| ARC-AGI-1 | 84% | — |
| CritPt | 8.3% | — |
| Mystery Game Puzzles | 6% | — |
Math Inkling-Small leads
Inkling-Small: 45.1 (#77), Mistral Small 3.1: 14.7 (#301)
| Benchmark | Inkling-Small | Mistral Small 3.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 90% | 3.9% |
| LMArena Math | 1459 | 1262 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 6% | — |
| Omni-MATH | — | 24.8% |
Knowledge Inkling-Small leads
Inkling-Small: 48.2 (#77), Mistral Small 3.1: 22.6 (#271)
| Benchmark | Inkling-Small | Mistral Small 3.1 |
|---|---|---|
| GPQA Diamond | 88.5% | 41.9% |
| LMArena Expert | 1442 | 1257 |
| SimpleQA Verified | 19.1% | — |
| MMLU-Pro | — | 61% |
| GPQA (HELM) | — | 39.2% |
Multimodal Inkling-Small leads
Inkling-Small: 39.1 (#62), Mistral Small 3.1: 33.2 (#99)
| Benchmark | Inkling-Small | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | 1235 | 1136 |
Multilingual Inkling-Small leads
Inkling-Small: 51.7 (#104), Mistral Small 3.1: 41.2 (#209)
| Benchmark | Inkling-Small | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1402 | 1255 |
| LMArena Chinese | 1465 | 1253 |
| LMArena French | 1436 | 1273 |
| LMArena German | 1405 | 1266 |
| LMArena Japanese | 1405 | 1208 |
| LMArena Korean | 1363 | 1206 |
| LMArena Russian | 1391 | 1263 |
| LMArena Spanish | 1428 | 1283 |
Instruction Following Inkling-Small leads
Inkling-Small: 73.8 (#114), Mistral Small 3.1: 63.6 (#230)
| Benchmark | Inkling-Small | Mistral Small 3.1 |
|---|---|---|
| LMArena Instruction Following | 1399 | 1264 |
| IFEval | — | 75% |
Long Context Inkling-Small leads
Inkling-Small: 42.7 (#118), Mistral Small 3.1: 39.5 (#178)
| Benchmark | Inkling-Small | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1401 | 1299 |
Writing & Preference Inkling-Small leads
Inkling-Small: 59.6 (#107), Mistral Small 3.1: 37.0 (#259)
| Benchmark | Inkling-Small | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1414 | 1277 |
| LMArena Creative Writing | 1331 | 1253 |
| EQ-Bench Creative Writing | 1491 | 761 |
| LMArena Multi-Turn | 1418 | 1270 |
| WildBench | — | 78.8% |
Frequently asked questions
Is Inkling-Small better than Mistral Small 3.1?
Inkling-Small is the stronger model overall, scoring 46.5 to 31.7 on the Noometry Index. Mistral Small 3.1 costs 1.6× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Which is cheaper, Inkling-Small or Mistral Small 3.1?
Mistral Small 3.1 is cheaper. It lists at $0.35 per million input tokens and $0.56 per million output tokens; Inkling-Small lists at $0.45 and $1.20.
Is Inkling-Small or Mistral Small 3.1 better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 38.3 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 128K.
How many benchmarks do Inkling-Small and Mistral Small 3.1 share?
23 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Mistral Small 3.1 has 28.