BlogLLM Benchmark Scores as Published, Side by Side
Ministral 3 14B Instruct 2512: Benchmark Scores as Published
Every result the catalog holds for Ministral 3 14B Instruct 2512: 5 tests in 2 areas, from 2 pages. Each was printed by the company named beside it. Each number is as printed; nothing is ranked or rescored.
Developer Mistral AIReleased 2025-12-02Context window 256KInput Text, imageWeights Open (Apache 2.0)Data version 2026103001, as of 2026-10-30
General Knowledge and Reasoning
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| FACTS Grounding (0 to 1) | 0.49 | AI21 Labs, AI21 Jamba2 Mini model cardchecked 2026-10-15 | - |
Instruction Following
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| IFBench | 27 | AI21 Labs, AI21 Jamba2 Mini model cardchecked 2026-10-15 | - |
| IFEval | 73% | AI21 Labs, AI21 Jamba2 Mini model cardchecked 2026-10-15 | - |
| COLLIE | 26% | AI21 Labs, AI21 Jamba2 Mini model cardchecked 2026-10-15 | - |
| Enterprise Reliability Score (average, 0 to 1) | 0.44 | AI21 Labs, AI21 Jamba2 Mini model cardchecked 2026-10-15 | - |
Price
API list prices in US dollars per one million tokens, as printed on the developer's pricing page on the day checked.
| Price | Value | Printed by | Setup as printed |
|---|---|---|---|
| Input | $0.2 | Mistral AI, Mistral API pricingchecked 2026-10-15 | - |
| Cached input | $0.02 | Mistral AI, Mistral API pricingchecked 2026-10-19 | - |
| Output | $0.2 | Mistral AI, Mistral API pricingchecked 2026-10-15 | - |
More from Mistral AI
Every number here is read from the same catalog file as the benchmark table, data version 2026103001. Where one page printed the model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.