Model comparison
Inkling vs Mistral Large 3
Inkling is the stronger model overall, scoring 44.1 to 39.1 on the Noometry Index. Mistral Large 3 costs 6.9× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Mistral AISummary
- They share 19 benchmarks with published results for both. Inkling scores higher in 7 categories and Mistral Large 3 in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.4 to 15.2.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Mistral Large 3 accepts more context: 262K tokens versus 66K.
Side by side
| Inkling | Mistral Large 3 | |
|---|---|---|
| Provider | Thinking Machines Lab | Mistral AI |
| Noometry Index | 44.1 | 39.1 |
| Released | 2026-07-15 | 2025-12-02 |
| Weights | Open | Open |
| Context window | 66K | 262K |
| Max output | 66K | 8K |
| Input $ / M tokens | $1.87 | $0.25 |
| Output $ / M tokens | $4.68 | $0.75 |
| Results tracked | 41 | 24 |
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 3: 34.4 (#237)
| Benchmark | Inkling | Mistral Large 3 |
|---|---|---|
| LMArena WebDev | 1413 | 1230 |
| LMArena Coding | 1464 | 1448 |
| FrontierCode | 14% | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |
| ALE-Bench | 946 | — |
Agentic & Tool Use Not comparable
Inkling: 29.6 (#85), Mistral Large 3: —
| Benchmark | Inkling | Mistral Large 3 |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
Reasoning Inkling leads
Inkling: 40.4 (#56), Mistral Large 3: 15.2 (#319)
| Benchmark | Inkling | Mistral Large 3 |
|---|---|---|
| LMArena Hard Prompts | 1451 | 1429 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| Kagi LLM Benchmark | — | 50.9% |
| NYT Connections (extended) | — | 7.5% |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| Chess Puzzles | 21% | — |
| Thematic Generalization | — | 23% |
| DTBench | 87.5% | — |
| LMCA | 37.6% | — |
| Epoch Capabilities Index | 148.54 | — |
Math Mistral Large 3 leads
Inkling: 31.3 (#225), Mistral Large 3: 38.7 (#129)
| Benchmark | Inkling | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1479 | 1414 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 0% | — |
Knowledge Inkling leads
Inkling: 55.1 (#49), Mistral Large 3: 36.0 (#177)
| Benchmark | Inkling | Mistral Large 3 |
|---|---|---|
| LMArena Expert | 1465 | 1421 |
| GPQA Diamond | 88.3% | — |
| SimpleQA Verified | 40.3% | — |
| Vectara Hallucination Rate | — | 14.5% |
Multimodal Not comparable
Inkling: —, Mistral Large 3: 38.2 (#66)
| Benchmark | Inkling | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1221 |
Multilingual Inkling leads
Inkling: 54.0 (#52), Mistral Large 3: 52.5 (#84)
| Benchmark | Inkling | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1434 | 1413 |
| LMArena Chinese | 1490 | 1447 |
| LMArena French | 1458 | 1455 |
| LMArena German | 1446 | 1437 |
| LMArena Japanese | 1429 | 1394 |
| LMArena Korean | 1404 | 1384 |
| LMArena Russian | 1429 | 1411 |
| LMArena Spanish | 1448 | 1440 |
Instruction Following Inkling leads
Inkling: 75.1 (#71), Mistral Large 3: 74.0 (#108)
| Benchmark | Inkling | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1426 | 1403 |
Long Context Too close to call
Inkling: 43.8 (#86), Mistral Large 3: 43.1 (#105)
| Benchmark | Inkling | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1434 | 1413 |
Writing & Preference Inkling leads
Inkling: 65.2 (#51), Mistral Large 3: 60.0 (#101)
| Benchmark | Inkling | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1441 | 1428 |
| LMArena Creative Writing | 1387 | 1386 |
| EQ-Bench Creative Writing | 1611 | 1412 |
| LMArena Multi-Turn | 1436 | 1429 |
| EQ-Bench 4 | 1226 | — |
Frequently asked questions
Is Inkling better than Mistral Large 3?
Inkling is the stronger model overall, scoring 44.1 to 39.1 on the Noometry Index. Mistral Large 3 costs 6.9× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Which is cheaper, Inkling or Mistral Large 3?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Inkling lists at $1.87 and $4.68.
Is Inkling or Mistral Large 3 better for coding?
They score almost the same on coding (34.5 vs 34.4); test both on your own repository before choosing.
Which has the bigger context window?
Mistral Large 3 does, with 262K tokens against 66K.
How many benchmarks do Inkling and Mistral Large 3 share?
19 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Mistral Large 3 has 24.