Mistral AIMixtral 8x7B
Mixtral 8x7B is a Mistral AI open-weights model, released 11 Dec 2023. Its best configuration ranks #782 of 785 on the BenchLeader Index at 31.7 ±5.0, in the lower half. The ± is the point: 51 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 composite (35) and lowest in instruction following (13). At $0.513 per million tokens blended it is mid-priced. Output speed of 25 tokens per second puts it in the slowest quarter, with a first answer in 1.1 s. Last measured 22 Oct 2026.
- Blended price
- $0.513/M
- $0.450 in · $0.700 out
- Output speed
- 25 tok/s
- measured by Artificial Analysis
- First answer
- 1.11 s
- first token 1.11 s
- Context
- 33k
- Full answer
- 21 s
- median, reasoning included
- Cost per run
- –
- Released
- 11 Dec 2023
- Overall index32
- Reasoning28
- Coding34
- Maths30
- Knowledge18
- Instruction following13
- Human preference33
- Composite35
How its index has moved
9 Sept 2026 to 20 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 | Trend |
|---|---|---|---|
| GPQA Diamond | 30.6%#271 | Epoch AI Benchmarking Hub | |
| Arena Hard Prompts | 1211#313 | Arena (LMArena) | |
| GPQA Diamond (AA)not in index | 29.2%#527 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 4.7%#480 | Artificial Analysis | |
| GPQA Diamond (HELM)not in index | 29.6%#63 | HELM Capabilities | |
| DTBenchnot in index | 49.6%#215 | Epoch AI Benchmarking Hub | |
| ForecastBenchnot in index | 58.2%#81 | ForecastBench | |
| HellaSwagnot in index | 86.7%#7 | Epoch AI Benchmarking Hub | |
| WinoGrandenot in index | 77.2%#25 | Epoch AI Benchmarking Hub | |
| ARC (AI2 Challenge)not in index | 87.3%#8 | Epoch AI Benchmarking Hub | |
| PIQAnot in index | 83.6%#10 | Epoch AI Benchmarking Hub | |
| ANLInot in index | 55.2%#5 | Epoch AI Benchmarking Hub |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Coding | 1240#312 | Arena (LMArena) |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| MATH Level 5 | 9.9%#90 | Epoch AI Benchmarking Hub | |
| Omni-MATH (HELM) | 10.5%#66 | HELM Capabilities | |
| Arena Maths | 1191#305 | Arena (LMArena) | |
| GSM8Knot in index | 74.4%#21 | Epoch AI Benchmarking Hub |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| LegalBench | 55.8%#136 | Vals AI | |
| MedQA | 53.2%#86 | Vals AI | |
| MMLU-Pro (HELM)not in index | 33.5%#63 | HELM Capabilities | |
| MMLUnot in index | 70.6%#51 | Epoch AI Benchmarking Hub | |
| TriviaQAnot in index | 82.2%#12 | Epoch AI Benchmarking Hub | |
| OpenBookQAnot in index | 85.8%#5 | Epoch AI Benchmarking Hub |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| IFEval (HELM) | 57.5%#67 | HELM Capabilities | |
| WildBench (HELM) | 67.3%#62 | HELM Capabilities | |
| Arena Instruction Followingnot in index | 1181#310 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1197#312 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1159#310 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1168#307 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1184#317 | Arena (LMArena) |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Epoch Capabilities Indexnot in index | 118.4#183 | Epoch AI Benchmarking Hub | |
| AA Intelligence Index v4.3.2 | 5.1#602 | Artificial Analysis | |
| HELM Capabilities meannot in index | 39.7%#65 | HELM Capabilities |
Price history
The price above, per 1M tokens, every day it changed.
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. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0004 | – | 13.1 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0058 | – | 25.1 s |
| Code edit | 6,000 / 1,500 | $0.0038 | – | 1.0 min |
| Agentic coding session | 60,000 / 4,000 | $0.030 | – | 2.7 min |
| Structured extraction | 2,000 / 200 | $0.0010 | – | 9.1 s |
More from Mistral AI
See also
Questions people ask
- What are Mixtral 8x7B's benchmark scores?
- As of 25 Oct 2026, Mixtral 8x7B scores 31.7 ±5.0 on the BenchLeader Index, strongest in composite (35) and weakest in instruction following (13). That rests on 12 independent benchmark results, and every score on this page links to its publisher.
- How does Mixtral 8x7B rank?
- Mixtral 8x7B is #782 of 785 ranked configurations on 25 Oct 2026. 51 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 Mixtral 8x7B cost per 1M tokens?
- As of 25 Oct 2026, Mixtral 8x7B costs $0.450 per 1M input tokens and $0.700 per 1M output tokens, $0.513 blended (three input tokens per output token). The list price last changed on 6 Oct 2026.
- When was Mixtral 8x7B released?
- Mistral AI released Mixtral 8x7B on 11 Dec 2023.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Mixtral 8x7B: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/mixtral-8x7b.