Model comparison
Inkling vs Mistral Medium 3.5
Inkling is the stronger model overall, scoring 44.1 to 40.2 on the Noometry Index.
Last verified . 19 shared benchmarks.
Mistral AISummary
- They share 19 benchmarks with published results for both. Inkling scores higher in 6 categories and Mistral Medium 3.5 in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.4 to 17.3.
- Inkling is cheaper at $1.87 / $4.68 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
- Mistral Medium 3.5 accepts more context: 262K tokens versus 66K.
Side by side
| Inkling | Mistral Medium 3.5 | |
|---|---|---|
| Provider | Thinking Machines Lab | Mistral AI |
| Noometry Index | 44.1 | 40.2 |
| Released | 2026-07-15 | — |
| Weights | Open | Open |
| Context window | 66K | 262K |
| Max output | 66K | 210K |
| Input $ / M tokens | $1.87 | $1.50 |
| Output $ / M tokens | $4.68 | $7.50 |
| Results tracked | 41 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium 3.5 leads
Inkling: 34.5 (#234), Mistral Medium 3.5: 36.0 (#213)
| Benchmark | Inkling | Mistral Medium 3.5 |
|---|---|---|
| LMArena WebDev | 1413 | 1264 |
| LMArena Coding | 1464 | 1461 |
| FrontierCode | 14% | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |
| ALE-Bench | 946 | — |
Agentic & Tool Use Not comparable
Inkling: 29.6 (#85), Mistral Medium 3.5: —
| Benchmark | Inkling | Mistral Medium 3.5 |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
Reasoning Inkling leads
Inkling: 40.4 (#56), Mistral Medium 3.5: 17.3 (#295)
| Benchmark | Inkling | Mistral Medium 3.5 |
|---|---|---|
| LMArena Hard Prompts | 1451 | 1436 |
| Epoch Capabilities Index | 148.54 | 141.35 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| Kagi LLM Benchmark | — | 41.4% |
| NYT Connections (extended) | — | 12.9% |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| Chess Puzzles | 21% | — |
| DTBench | 87.5% | — |
| LMCA | 37.6% | — |
Math Mistral Medium 3.5 leads
Inkling: 31.3 (#225), Mistral Medium 3.5: 39.1 (#113)
| Benchmark | Inkling | Mistral Medium 3.5 |
|---|---|---|
| LMArena Math | 1479 | 1431 |
| 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 Medium 3.5: 40.0 (#126)
| Benchmark | Inkling | Mistral Medium 3.5 |
|---|---|---|
| LMArena Expert | 1465 | 1432 |
| GPQA Diamond | 88.3% | — |
| SimpleQA Verified | 40.3% | — |
Multimodal Not comparable
Inkling: —, Mistral Medium 3.5: 38.3 (#65)
| Benchmark | Inkling | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | — | 1223 |
Multilingual Inkling leads
Inkling: 54.0 (#52), Mistral Medium 3.5: 51.9 (#100)
| Benchmark | Inkling | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | 1434 | 1404 |
| LMArena Chinese | 1490 | 1442 |
| LMArena French | 1458 | 1448 |
| LMArena German | 1446 | 1451 |
| LMArena Korean | 1404 | 1385 |
| LMArena Russian | 1429 | 1395 |
| LMArena Spanish | 1448 | 1409 |
| LMArena Japanese | 1429 | — |
Instruction Following Too close to call
Inkling: 75.1 (#71), Mistral Medium 3.5: 74.6 (#90)
| Benchmark | Inkling | Mistral Medium 3.5 |
|---|---|---|
| LMArena Instruction Following | 1426 | 1415 |
Long Context Too close to call
Inkling: 43.8 (#86), Mistral Medium 3.5: 43.2 (#103)
| Benchmark | Inkling | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | 1434 | 1415 |
Writing & Preference Inkling leads
Inkling: 65.2 (#51), Mistral Medium 3.5: 58.5 (#117)
| Benchmark | Inkling | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | 1441 | 1421 |
| LMArena Creative Writing | 1387 | 1374 |
| EQ-Bench 4 | 1226 | 993 |
| LMArena Multi-Turn | 1436 | 1423 |
| EQ-Bench Creative Writing | 1611 | — |
Frequently asked questions
Is Inkling better than Mistral Medium 3.5?
Inkling is the stronger model overall, scoring 44.1 to 40.2 on the Noometry Index.
Which is cheaper, Inkling or Mistral Medium 3.5?
Inkling is cheaper. It lists at $1.87 per million input tokens and $4.68 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.
Is Inkling or Mistral Medium 3.5 better for coding?
Mistral Medium 3.5 scores higher on coding benchmarks: 36.0 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium 3.5 does, with 262K tokens against 66K.
How many benchmarks do Inkling and Mistral Medium 3.5 share?
19 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Mistral Medium 3.5 has 22.