Mistral AIMinistral 3 14B
Ministral 3 14B is a Mistral AI open-weights model, released 2 Dec 2025. Its best configuration ranks #684 of 785 on the BenchLeader Index at 39.5 ±2.0, in the lower half. The ± is the point: 222 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in reasoning (41) and lowest in knowledge (32). At $0.200 per million tokens blended it is cheaper than most ranked models. Output speed of 83 tokens per second puts it slower than most, with a first answer in 0.9 s. Last measured 2 Dec 2025.stale: no new result in six months
- Blended price
- $0.200/M
- $0.200 in · $0.200 out
- Output speed
- 83 tok/s
- measured by Artificial Analysis
- First answer
- 0.95 s
- first token 0.34 s
- Context
- 262k
- Full answer
- 6.97 s
- median, reasoning included
- Cost per run
- $0.019
- one full Intelligence Index run
- Released
- 2 Dec 2025
- Overall index40
- Reasoning41
- Agents & tools35
- Knowledge32
- Instruction following36
- Multimodal32
- Long context37
- Composite36
How its index has moved
9 Sept 2026 to 21 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source |
|---|---|---|
| GPQA Diamond (AA)not in index | 57.2%#394 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 4.6%#484 | Artificial Analysis |
| CritPt | 0.0%#315 | Artificial Analysis |
Coding
| Benchmark | not stated | Source |
|---|---|---|
| SciCode (AA)not in index | 23.8%#222 | Artificial Analysis |
| Terminal-Bench 4.0 (AA)not in index | 0.0%#152 | Artificial Analysis |
| Terminal-Bench 2.1 (AA)not in index | 9.7%#196 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source |
|---|---|---|
| Terminal-Bench Hard | 4.5%#284 | Artificial Analysis |
| τ²-Bench Telecom (AA)not in index | 27.2%#277 | Artificial Analysis |
| GDPval-AA v2.1not in index | 0.0%#124 | Artificial Analysis |
| τ³-Banking (AA) | 6.6%#166 | Artificial Analysis |
| AutomationBenchnot in index | 0.6%#204 | Artificial Analysis |
| GDP.pdf (AA)not in index | 1.2%#198 | Artificial Analysis |
Knowledge
| Benchmark | not stated | Source |
|---|---|---|
| AA-Omniscience | -66.4#504 | Artificial Analysis |
| AA-Omniscience: accuracynot in index | 13.6%#454 | Artificial Analysis |
| AA-Omniscience: non-hallucinationnot in index | 7.5%#482 | Artificial Analysis |
Instruction following
| Benchmark | not stated | Source |
|---|---|---|
| IFBench | 32.0%#344 | Artificial Analysis |
Multimodal
| Benchmark | not stated | Source |
|---|---|---|
| MMMU-Pro | 49.8%#242 | Artificial Analysis |
Long context
| Benchmark | not stated | Source |
|---|---|---|
| AA-LCR | 26.3%#407 | Artificial Analysis |
| MLCRnot in index | 2.2%#158 | Artificial Analysis |
Composite
| Benchmark | not stated | Source |
|---|---|---|
| AA Intelligence Index v4.3.2 | 6.0#544 | Artificial Analysis |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Mistral | 94 tok/s | 0.34 s | $0.200 | $0.200 | 262k | – |
| Mistral | 92 tok/s | 0.35 s | $0.200 | $0.200 | 262k | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.020 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0001 | $0.0001 | 4.6 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0025 | $0.0009 | 8.2 s |
| Code edit | 6,000 / 1,500 | $0.0015 | $0.0007 | 19.0 s |
| Agentic coding session | 60,000 / 4,000 | $0.013 | $0.0047 | 49.1 s |
| Structured extraction | 2,000 / 200 | $0.0004 | $0.0002 | 3.4 s |
More from Mistral AI
See also
Questions people ask
- What are Ministral 3 14B's benchmark scores?
- As of 24 Oct 2026, Ministral 3 14B scores 39.5 ±2.0 on the BenchLeader Index, strongest in reasoning (41) and weakest in knowledge (32). That rests on 8 independent benchmark results, and every score on this page links to its publisher.
- How does Ministral 3 14B rank?
- Ministral 3 14B is #684 of 785 ranked configurations on 24 Oct 2026. 222 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- How much does Ministral 3 14B cost per 1M tokens?
- As of 24 Oct 2026, Ministral 3 14B costs $0.200 per 1M input tokens and $0.200 per 1M output tokens, $0.200 blended (three input tokens per output token).
- When was Ministral 3 14B released?
- Mistral AI released Ministral 3 14B on 2 Dec 2025.
Data as of 24 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Ministral 3 14B: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/ministral-3-14b.