Model comparison
Inkling vs Mistral Large
Inkling is the stronger model overall, scoring 44.1 to 31.9 on the Noometry Index.
Last verified . 27 shared benchmarks.
Mistral AISummary
- They share 27 benchmarks with published results for both. Inkling scores higher in 9 categories and Mistral Large in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.1 to 30.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for Inkling and 8.5% for Mistral Large.
- Inkling is cheaper at $1.87 / $4.68 per million input/output tokens, against $2 / $6 for Mistral Large.
- Mistral Large accepts more context: 131K tokens versus 66K.
Side by side
| Inkling | Mistral Large | |
|---|---|---|
| Provider | Thinking Machines Lab | Mistral AI |
| Noometry Index | 44.1 | 31.9 |
| Released | 2026-07-15 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 66K | 131K |
| Max output | 66K | 16K |
| Input $ / M tokens | $1.87 | $2 |
| Output $ / M tokens | $4.68 | $6 |
| Results tracked | 41 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Inkling: 34.5 (#234), Mistral Large: 34.3 (#240)
| Benchmark | Inkling | Mistral Large |
|---|---|---|
| SciCode | 47% | 36.2% |
| LMArena Coding | 1464 | 1277 |
| ALE-Bench | 946 | 264.7 |
| FrontierCode | 14% | — |
| LMArena WebDev | 1413 | — |
| FrontierSWE | 4.1% | — |
| WeirdML | 32.3% | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Too close to call
Inkling: 29.6 (#85), Mistral Large: 28.6 (#89)
| Benchmark | Inkling | Mistral Large |
|---|---|---|
| APEX-Agents | 33.8% | — |
| Berkeley Function Calling Leaderboard | — | 38.4% |
| τ²-bench Banking | 25% | — |
Reasoning Inkling leads
Inkling: 40.4 (#56), Mistral Large: 15.8 (#310)
| Benchmark | Inkling | Mistral Large |
|---|---|---|
| SimpleBench | 50% | 22.5% |
| CritPt | 5.4% | 0% |
| LMArena Hard Prompts | 1451 | 1257 |
| DTBench | 87.5% | 65.1% |
| LMCA | 37.6% | 16.7% |
| Epoch Capabilities Index | 148.54 | 128.52 |
| ARC-AGI-2 | 36.5% | — |
| ARC-AGI-1 | 79.5% | — |
| Chess Puzzles | 21% | — |
| LiveBench Reasoning | — | 43.5% |
| LiveBench Data Analysis | — | 50.1% |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |
Math Inkling leads
Inkling: 31.3 (#225), Mistral Large: 18.2 (#291)
| Benchmark | Inkling | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 8.5% |
| LMArena Math | 1479 | 1262 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| ProofBench | 0% | — |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Inkling leads
Inkling: 55.1 (#49), Mistral Large: 30.1 (#230)
| Benchmark | Inkling | Mistral Large |
|---|---|---|
| GPQA Diamond | 88.3% | 51.3% |
| LMArena Expert | 1465 | 1232 |
| SimpleQA Verified | 40.3% | — |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |
Multilingual Inkling leads
Inkling: 54.0 (#52), Mistral Large: 40.0 (#219)
| Benchmark | Inkling | Mistral Large |
|---|---|---|
| LMArena Non-English | 1434 | 1237 |
| LMArena Chinese | 1490 | 1240 |
| LMArena French | 1458 | 1325 |
| LMArena German | 1446 | 1254 |
| LMArena Japanese | 1429 | 1188 |
| LMArena Korean | 1404 | 1202 |
| LMArena Russian | 1429 | 1257 |
| LMArena Spanish | 1448 | 1268 |
Instruction Following Inkling leads
Inkling: 75.1 (#71), Mistral Large: 67.9 (#191)
| Benchmark | Inkling | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1426 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context Inkling leads
Inkling: 43.8 (#86), Mistral Large: 38.3 (#199)
| Benchmark | Inkling | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1434 | 1261 |
Writing & Preference Inkling leads
Inkling: 65.2 (#51), Mistral Large: 40.7 (#242)
| Benchmark | Inkling | Mistral Large |
|---|---|---|
| LMArena Text | 1441 | 1266 |
| LMArena Creative Writing | 1387 | 1243 |
| EQ-Bench Creative Writing | 1611 | 985 |
| LMArena Multi-Turn | 1436 | 1260 |
| Short-Story Creative Writing | — | 69% |
| WildBench | — | 80.1% |
| EQ-Bench 4 | 1226 | — |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is Inkling better than Mistral Large?
Inkling is the stronger model overall, scoring 44.1 to 31.9 on the Noometry Index.
Which is cheaper, Inkling or Mistral Large?
Inkling is cheaper. It lists at $1.87 per million input tokens and $4.68 per million output tokens; Mistral Large lists at $2 and $6.
Is Inkling or Mistral Large better for coding?
They score almost the same on coding (34.5 vs 34.3); test both on your own repository before choosing.
Which has the bigger context window?
Mistral Large does, with 131K tokens against 66K.
How many benchmarks do Inkling and Mistral Large share?
27 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Mistral Large has 51.