Model comparison
Inkling vs Ministral 3B
Inkling is the stronger model overall, scoring 44.1 to 26.2 on the Noometry Index. Ministral 3B costs 26× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
Mistral AISummary
- They share 4 benchmarks with published results for both. Inkling scores higher in 3 categories and Ministral 3B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.1 to 10.4.
- The biggest single-benchmark swing is GPQA Diamond: 88.3% for Inkling and 25.3% for Ministral 3B.
- Ministral 3B is cheaper at $0.10 / $0.10 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Ministral 3B accepts more context: 131K tokens versus 66K.
Side by side
| Inkling | Ministral 3B | |
|---|---|---|
| Provider | Thinking Machines Lab | Mistral AI |
| Noometry Index | 44.1 | 26.2 |
| Released | 2026-07-15 | 2024-10-01 |
| Weights | Open | Open |
| Context window | 66K | 131K |
| Max output | 66K | 262K |
| Input $ / M tokens | $1.87 | $0.10 |
| Output $ / M tokens | $4.68 | $0.10 |
| Results tracked | 41 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Inkling: 34.5 (#234), Ministral 3B: —
| Benchmark | Inkling | Ministral 3B |
|---|---|---|
| FrontierCode | 14% | — |
| LMArena WebDev | 1413 | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |
| LMArena Coding | 1464 | — |
| ALE-Bench | 946 | — |
Agentic & Tool Use Not comparable
Inkling: 29.6 (#85), Ministral 3B: —
| Benchmark | Inkling | Ministral 3B |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
Reasoning Inkling leads
Inkling: 40.4 (#56), Ministral 3B: 18.4 (#282)
| Benchmark | Inkling | Ministral 3B |
|---|---|---|
| DTBench | 87.5% | 51.7% |
| LMCA | 37.6% | 5.5% |
| Epoch Capabilities Index | 148.54 | 118.1 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| Chess Puzzles | 21% | — |
| LMArena Hard Prompts | 1451 | — |
Math Inkling leads
Inkling: 31.3 (#225), Ministral 3B: 26.6 (#258)
| Benchmark | Inkling | Ministral 3B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 0% | — |
| LMArena Math | 1479 | — |
| MATH Level 5 | — | 14.4% |
Knowledge Inkling leads
Inkling: 55.1 (#49), Ministral 3B: 10.4 (#302)
| Benchmark | Inkling | Ministral 3B |
|---|---|---|
| GPQA Diamond | 88.3% | 25.3% |
| SimpleQA Verified | 40.3% | — |
| Vectara Hallucination Rate | — | 7.3% |
| LMArena Expert | 1465 | — |
Multilingual Not comparable
Inkling: 54.0 (#52), Ministral 3B: —
| Benchmark | Inkling | Ministral 3B |
|---|---|---|
| LMArena Non-English | 1434 | — |
| LMArena Chinese | 1490 | — |
| LMArena French | 1458 | — |
| LMArena German | 1446 | — |
| LMArena Japanese | 1429 | — |
| LMArena Korean | 1404 | — |
| LMArena Russian | 1429 | — |
| LMArena Spanish | 1448 | — |
Instruction Following Not comparable
Inkling: 75.1 (#71), Ministral 3B: —
| Benchmark | Inkling | Ministral 3B |
|---|---|---|
| LMArena Instruction Following | 1426 | — |
Long Context Not comparable
Inkling: 43.8 (#86), Ministral 3B: —
| Benchmark | Inkling | Ministral 3B |
|---|---|---|
| LMArena Longer Query | 1434 | — |
Writing & Preference Not comparable
Inkling: 65.2 (#51), Ministral 3B: —
| Benchmark | Inkling | Ministral 3B |
|---|---|---|
| LMArena Text | 1441 | — |
| LMArena Creative Writing | 1387 | — |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
| LMArena Multi-Turn | 1436 | — |
Frequently asked questions
Is Inkling better than Ministral 3B?
Inkling is the stronger model overall, scoring 44.1 to 26.2 on the Noometry Index. Ministral 3B costs 26× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Which is cheaper, Inkling or Ministral 3B?
Ministral 3B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; Inkling lists at $1.87 and $4.68.
Which has the bigger context window?
Ministral 3B does, with 131K tokens against 66K.
How many benchmarks do Inkling and Ministral 3B share?
4 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Ministral 3B has 6.