Model comparison
Inkling-Small vs Mistral Medium
Inkling-Small is the stronger model overall, scoring 46.5 to 36.3 on the Noometry Index.
Last verified . 23 shared benchmarks.
Mistral AISummary
- They share 23 benchmarks with published results for both. Inkling-Small scores higher in 6 categories and Mistral Medium in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling-Small leads 48.2 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 90% for Inkling-Small and 32.2% for Mistral Medium.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Inkling-Small accepts more context: 524K tokens versus 262K.
Side by side
| Inkling-Small | Mistral Medium | |
|---|---|---|
| Provider | Thinking Machines Lab | Mistral AI |
| Noometry Index | 46.5 | 36.3 |
| Released | 2026-07-15 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 524K | 262K |
| Max output | 1.05M | 262K |
| Input $ / M tokens | $0.45 | $1.50 |
| Output $ / M tokens | $1.20 | $7.50 |
| Results tracked | 33 | 36 |
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 Medium: 34.2 (#243)
| Benchmark | Inkling-Small | Mistral Medium |
|---|---|---|
| SciCode | 48.7% | 40.2% |
| LMArena Coding | 1451 | 1434 |
| FrontierCode | — | 8% |
| LMArena WebDev | 1409 | — |
| WeirdML | — | 43.7% |
| ALE-Bench | — | 763.98 |
Agentic & Tool Use Not comparable
Inkling-Small: —, Mistral Medium: 28.3 (#90)
| Benchmark | Inkling-Small | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
Reasoning Inkling-Small leads
Inkling-Small: 38.6 (#63), Mistral Medium: 24.0 (#167)
| Benchmark | Inkling-Small | Mistral Medium |
|---|---|---|
| CritPt | 8.3% | 0% |
| LMArena Hard Prompts | 1423 | 1426 |
| ARC-AGI-2 | 40.1% | — |
| Kagi LLM Benchmark | — | 50% |
| ARC-AGI-1 | 84% | — |
| Chess Puzzles | 18% | — |
| Mystery Game Puzzles | 6% | — |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 150.15 | — |
Math Inkling-Small leads
Inkling-Small: 45.1 (#77), Mistral Medium: 28.1 (#245)
| Benchmark | Inkling-Small | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 90% | 32.2% |
| ProofBench | 6% | 9% |
| LMArena Math | 1459 | 1408 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Inkling-Small leads
Inkling-Small: 48.2 (#77), Mistral Medium: 25.0 (#265)
| Benchmark | Inkling-Small | Mistral Medium |
|---|---|---|
| GPQA Diamond | 88.5% | 59.5% |
| LMArena Expert | 1442 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| SimpleQA Verified | 19.1% | — |
| Vectara Hallucination Rate | — | 22.7% |
Multimodal Inkling-Small leads
Inkling-Small: 39.1 (#62), Mistral Medium: 35.3 (#88)
| Benchmark | Inkling-Small | Mistral Medium |
|---|---|---|
| LMArena Vision | 1235 | 1172 |
Multilingual Too close to call
Inkling-Small: 51.7 (#104), Mistral Medium: 52.1 (#91)
| Benchmark | Inkling-Small | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1402 | 1408 |
| LMArena Chinese | 1465 | 1447 |
| LMArena French | 1436 | 1459 |
| LMArena German | 1405 | 1432 |
| LMArena Japanese | 1405 | 1378 |
| LMArena Korean | 1363 | 1380 |
| LMArena Russian | 1391 | 1411 |
| LMArena Spanish | 1428 | 1433 |
Instruction Following Too close to call
Inkling-Small: 73.8 (#114), Mistral Medium: 73.7 (#116)
| Benchmark | Inkling-Small | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1399 | 1398 |
Long Context Too close to call
Inkling-Small: 42.7 (#118), Mistral Medium: 42.9 (#114)
| Benchmark | Inkling-Small | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1401 | 1406 |
Writing & Preference Too close to call
Inkling-Small: 59.6 (#107), Mistral Medium: 60.0 (#103)
| Benchmark | Inkling-Small | Mistral Medium |
|---|---|---|
| LMArena Text | 1414 | 1424 |
| LMArena Creative Writing | 1331 | 1391 |
| LMArena Multi-Turn | 1418 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| EQ-Bench Creative Writing | 1491 | — |
Frequently asked questions
Is Inkling-Small better than Mistral Medium?
Inkling-Small is the stronger model overall, scoring 46.5 to 36.3 on the Noometry Index.
Which is cheaper, Inkling-Small or Mistral Medium?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Inkling-Small or Mistral Medium better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 262K.
How many benchmarks do Inkling-Small and Mistral Medium share?
23 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Mistral Medium has 36.