Model comparison
Inkling-Small vs Mistral Large
Inkling-Small is the stronger model overall, scoring 46.5 to 31.6 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 8 categories and Mistral Large in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Inkling-Small leads 44.9 to 17.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 90% for Inkling-Small and 8.5% for Mistral Large.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $2 / $6 for Mistral Large.
- Inkling-Small accepts more context: 524K tokens versus 131K.
Side by side
| Inkling-Small | Mistral Large | |
|---|---|---|
| Provider | Thinking Machines Lab | Mistral AI |
| Noometry Index | 46.5 | 31.6 |
| Released | 2026-07-15 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 524K | 131K |
| Max output | 1.05M | 16K |
| Input $ / M tokens | $0.45 | $2 |
| Output $ / M tokens | $1.20 | $6 |
| Results tracked | 33 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Inkling-Small: 43.3 (#80), Mistral Large: 33.8 (#240)
| Benchmark | Inkling-Small | Mistral Large |
|---|---|---|
| SciCode | 48.7% | 36.2% |
| LMArena Coding | 1451 | 1277 |
| LMArena WebDev | 1408 | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| ALE-Bench | — | 264.7 |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Not comparable
Inkling-Small: —, Mistral Large: 28.4 (#83)
| Benchmark | Inkling-Small | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
Reasoning Inkling-Small leads
Inkling-Small: 39.0 (#53), Mistral Large: 15.4 (#305)
| Benchmark | Inkling-Small | Mistral Large |
|---|---|---|
| CritPt | 8.3% | 0% |
| LMArena Hard Prompts | 1424 | 1257 |
| Epoch Capabilities Index | 150.13 | 128.52 |
| ARC-AGI-2 | 40.1% | — |
| SimpleBench | — | 22.5% |
| ARC-AGI-1 | 84% | — |
| Chess Puzzles | 18% | — |
| LiveBench Reasoning | — | 43.5% |
| Mystery Game Puzzles | 6% | — |
| DTBench | — | 65.1% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |
Math Inkling-Small leads
Inkling-Small: 44.9 (#65), Mistral Large: 17.1 (#285)
| Benchmark | Inkling-Small | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 90% | 8.5% |
| LMArena Math | 1453 | 1262 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 6% | — |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Inkling-Small leads
Inkling-Small: 48.3 (#71), Mistral Large: 30.0 (#224)
| Benchmark | Inkling-Small | Mistral Large |
|---|---|---|
| GPQA Diamond | 88.5% | 51.3% |
| LMArena Expert | 1442 | 1232 |
| SimpleQA Verified | 19.1% | — |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |
Multimodal Not comparable
Inkling-Small: 38.4 (#59), Mistral Large: —
| Benchmark | Inkling-Small | Mistral Large |
|---|---|---|
| LMArena Vision | 1235 | — |
Multilingual Inkling-Small leads
Inkling-Small: 51.7 (#102), Mistral Large: 40.1 (#214)
| Benchmark | Inkling-Small | Mistral Large |
|---|---|---|
| LMArena Non-English | 1400 | 1237 |
| LMArena Chinese | 1458 | 1240 |
| LMArena French | 1438 | 1324 |
| LMArena German | 1412 | 1254 |
| LMArena Japanese | 1399 | 1187 |
| LMArena Korean | 1355 | 1202 |
| LMArena Russian | 1392 | 1257 |
| LMArena Spanish | 1426 | 1268 |
Instruction Following Inkling-Small leads
Inkling-Small: 73.9 (#112), Mistral Large: 68.1 (#186)
| Benchmark | Inkling-Small | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1397 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context Inkling-Small leads
Inkling-Small: 42.7 (#113), Mistral Large: 38.3 (#194)
| Benchmark | Inkling-Small | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1401 | 1262 |
Writing & Preference Inkling-Small leads
Inkling-Small: 59.8 (#102), Mistral Large: 40.9 (#237)
| Benchmark | Inkling-Small | Mistral Large |
|---|---|---|
| LMArena Text | 1413 | 1266 |
| LMArena Creative Writing | 1330 | 1243 |
| EQ-Bench Creative Writing | 1491 | 985 |
| LMArena Multi-Turn | 1420 | 1260 |
| Short-Story Creative Writing | — | 69% |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is Inkling-Small better than Mistral Large?
Inkling-Small is the stronger model overall, scoring 46.5 to 31.6 on the Noometry Index.
Which is cheaper, Inkling-Small or Mistral Large?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Mistral Large lists at $2 and $6.
Is Inkling-Small or Mistral Large better for coding?
Inkling-Small scores higher on coding benchmarks: 43.3 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 131K.
How many benchmarks do Inkling-Small and Mistral Large share?
23 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Mistral Large has 51.