Model comparison
Inkling vs Mistral Large 4
Inkling is the stronger model overall, scoring 44.1 to 43.1 on the Noometry Index. Mistral Large 4 costs 2.5× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
Mistral AISummary
- They share 14 benchmarks with published results for both. Inkling scores higher in 6 categories and Mistral Large 4 in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.1 to 36.6.
- The biggest single-benchmark swing is SimpleQA Verified: 40.3% for Inkling and 20% for Mistral Large 4.
- Mistral Large 4 is cheaper at $0.68 / $2.09 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Mistral Large 4 accepts more context: 1.05M tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| Inkling | Mistral Large 4 | |
|---|---|---|
| Provider | Thinking Machines Lab | Mistral AI |
| Noometry Index | 44.1 | 43.1 |
| Released | 2026-07-15 | 2026-10-06 |
| Weights | Open | Proprietary |
| Context window | 66K | 1.05M |
| Max output | 66K | 262K |
| Input $ / M tokens | $1.87 | $0.68 |
| Output $ / M tokens | $4.68 | $2.09 |
| Results tracked | 41 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 4 leads
Inkling: 34.5 (#234), Mistral Large 4: 48.6 (#57)
| Benchmark | Inkling | Mistral Large 4 |
|---|---|---|
| LMArena WebDev | 1413 | 1541 |
| LMArena Coding | 1464 | 1475 |
| FrontierCode | 14% | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |
| ALE-Bench | 946 | — |
Agentic & Tool Use Not comparable
Inkling: 29.6 (#85), Mistral Large 4: —
| Benchmark | Inkling | Mistral Large 4 |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
Reasoning Inkling leads
Inkling: 40.4 (#56), Mistral Large 4: 22.5 (#192)
| Benchmark | Inkling | Mistral Large 4 |
|---|---|---|
| LMArena Hard Prompts | 1451 | 1444 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| NYT Connections (extended) | — | 27.4% |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| Chess Puzzles | 21% | — |
| DTBench | 87.5% | — |
| LMCA | 37.6% | — |
| Epoch Capabilities Index | 148.54 | — |
Math Mistral Large 4 leads
Inkling: 31.3 (#225), Mistral Large 4: 40.4 (#91)
| Benchmark | Inkling | Mistral Large 4 |
|---|---|---|
| LMArena Math | 1479 | 1488 |
| 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 4: 36.6 (#166)
| Benchmark | Inkling | Mistral Large 4 |
|---|---|---|
| SimpleQA Verified | 40.3% | 20% |
| LMArena Expert | 1465 | 1447 |
| GPQA Diamond | 88.3% | — |
Multilingual Inkling leads
Inkling: 54.0 (#52), Mistral Large 4: 52.6 (#82)
| Benchmark | Inkling | Mistral Large 4 |
|---|---|---|
| LMArena Non-English | 1434 | 1415 |
| LMArena Chinese | 1490 | 1491 |
| LMArena Russian | 1429 | 1414 |
| LMArena French | 1458 | — |
| LMArena German | 1446 | — |
| LMArena Japanese | 1429 | — |
| LMArena Korean | 1404 | — |
| LMArena Spanish | 1448 | — |
Instruction Following Too close to call
Inkling: 75.1 (#71), Mistral Large 4: 75.0 (#76)
| Benchmark | Inkling | Mistral Large 4 |
|---|---|---|
| LMArena Instruction Following | 1426 | 1424 |
Long Context Too close to call
Inkling: 43.8 (#86), Mistral Large 4: 43.6 (#89)
| Benchmark | Inkling | Mistral Large 4 |
|---|---|---|
| LMArena Longer Query | 1434 | 1429 |
Writing & Preference Inkling leads
Inkling: 65.2 (#51), Mistral Large 4: 60.4 (#97)
| Benchmark | Inkling | Mistral Large 4 |
|---|---|---|
| LMArena Text | 1441 | 1427 |
| LMArena Creative Writing | 1387 | 1361 |
| LMArena Multi-Turn | 1436 | 1424 |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
Frequently asked questions
Is Inkling better than Mistral Large 4?
Inkling is the stronger model overall, scoring 44.1 to 43.1 on the Noometry Index. Mistral Large 4 costs 2.5× 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 4?
Mistral Large 4 is cheaper. It lists at $0.68 per million input tokens and $2.09 per million output tokens; Inkling lists at $1.87 and $4.68.
Is Inkling or Mistral Large 4 better for coding?
Mistral Large 4 scores higher on coding benchmarks: 48.6 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 4 does, with 1.05M tokens against 66K.
How many benchmarks do Inkling and Mistral Large 4 share?
14 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Mistral Large 4 has 15.