Model comparison
Codestral vs Inkling-Small
Inkling-Small is the stronger model overall, scoring 46.5 to 30.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AISummary
- The widest gap is in reasoning, where Inkling-Small leads 39.0 to 19.1.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Inkling-Small accepts more context: 524K tokens versus 256K.
Side by side
| Codestral | Inkling-Small | |
|---|---|---|
| Provider | Mistral AI | Thinking Machines Lab |
| Noometry Index | 30.1 | 46.5 |
| Released | 2024-05-29 | 2026-07-15 |
| Weights | Open | Open |
| Context window | 256K | 524K |
| Max output | 4K | 1.05M |
| Input $ / M tokens | $0.30 | $0.45 |
| Output $ / M tokens | $0.90 | $1.20 |
| Results tracked | 7 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Codestral: 26.9 (#316), Inkling-Small: 43.3 (#80)
| Benchmark | Codestral | Inkling-Small |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1408 |
| SciCode | — | 48.7% |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1451 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Inkling-Small leads
Codestral: 19.1 (#244), Inkling-Small: 39.0 (#53)
| Benchmark | Codestral | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | — | 40.1% |
| Kagi LLM Benchmark | 32.5% | — |
| ARC-AGI-1 | — | 84% |
| CritPt | — | 8.3% |
| Chess Puzzles | — | 18% |
| LMArena Hard Prompts | — | 1424 |
| Mystery Game Puzzles | — | 6% |
| Epoch Capabilities Index | — | 150.13 |
Math Not comparable
Codestral: —, Inkling-Small: 44.9 (#65)
| Benchmark | Codestral | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| OTIS Mock AIME 2024-2025 | — | 90% |
| ProofBench | — | 6% |
| LMArena Math | — | 1453 |
Knowledge Not comparable
Codestral: —, Inkling-Small: 48.3 (#71)
| Benchmark | Codestral | Inkling-Small |
|---|---|---|
| GPQA Diamond | — | 88.5% |
| SimpleQA Verified | — | 19.1% |
| LMArena Expert | — | 1442 |
Multimodal Not comparable
Codestral: —, Inkling-Small: 38.4 (#59)
| Benchmark | Codestral | Inkling-Small |
|---|---|---|
| LMArena Vision | — | 1235 |
Multilingual Not comparable
Codestral: —, Inkling-Small: 51.7 (#102)
| Benchmark | Codestral | Inkling-Small |
|---|---|---|
| LMArena Non-English | — | 1400 |
| LMArena Chinese | — | 1458 |
| LMArena French | — | 1438 |
| LMArena German | — | 1412 |
| LMArena Japanese | — | 1399 |
| LMArena Korean | — | 1355 |
| LMArena Russian | — | 1392 |
| LMArena Spanish | — | 1426 |
Instruction Following Not comparable
Codestral: —, Inkling-Small: 73.9 (#112)
| Benchmark | Codestral | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | — | 1397 |
Long Context Not comparable
Codestral: —, Inkling-Small: 42.7 (#113)
| Benchmark | Codestral | Inkling-Small |
|---|---|---|
| LMArena Longer Query | — | 1401 |
Writing & Preference Not comparable
Codestral: —, Inkling-Small: 59.8 (#102)
| Benchmark | Codestral | Inkling-Small |
|---|---|---|
| LMArena Text | — | 1413 |
| LMArena Creative Writing | — | 1330 |
| EQ-Bench Creative Writing | — | 1491 |
| LMArena Multi-Turn | — | 1420 |
Frequently asked questions
Is Codestral better than Inkling-Small?
Inkling-Small is the stronger model overall, scoring 46.5 to 30.1 on the Noometry Index.
Which is cheaper, Codestral or Inkling-Small?
Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; Inkling-Small lists at $0.45 and $1.20.
Is Codestral or Inkling-Small better for coding?
Inkling-Small scores higher on coding benchmarks: 43.3 versus 26.9 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 256K.
How many benchmarks do Codestral and Inkling-Small share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Inkling-Small has 33.