Open weights available
The weights are public. 4 of the 8 peers that say either way have open weights.
Mistral AI · Chat
Mixtral-8x7B is a sparse mixture-of-experts model with open weights, delivering fast, high-performance inference that outperforms Llama 2 70B and rivals GPT-3.5.
Evidence and sources
The weights are public. 4 of the 8 peers that say either way have open weights.
The maker plans to deprecate it on 30 Mar 2027, within the next 180 days.
Supported operations and provider-stated features
| 32K | |||
| 33K | $0.40 | $0.40 | |
| 33K | $0.60 | $0.60 | |
| 4K | $0.30 | $1.00 | |
| 16K | $0.15 | $0.15 | |
| 33K | $0.40 | $0.40 | |
| 32K | $0.70 | $0.70 | |
| 33K | $0.60 | $0.60 |
3 listings without a price are hidden.
Named effort levels run from lowest to highest. Select a result to see its source details.
| Benchmark | Score |
|---|---|
| Safety: BBQ - BBQ accuracy | |
| AIR-Bench: AIRBench 2024 - #1: Confidentiality | |
| AIR-Bench: AIRBench 2024 - #2: Integrity | |
| AIR-Bench: AIRBench 2024 - #3: Availability |
| Benchmark | Score |
|---|---|
| Arena ELO | |
| Chinese | |
| Creative Writing | |
| English |
| Benchmark | Mixtral-8x7B · · 12.9B/46.7B · |
|---|---|
| 4K | |
| 8K | |
| 16K | |
| 32K |
| Benchmark | Mixtral-8x7B · · 12.9B/46.7B · |
|---|---|
| 64K | |
| 128K | |
| Avg | |
| wAvg (dec) | |
| wAvg (inc) |
| Benchmark | Score |
|---|---|
| Pass@1 | |
| Elo Rating | |
| Elo Rating (Div. 1 + 2) | |
| Elo Rating (Div. 2) |
| Benchmark | completion/024664d | qa/chat/00e933e |
|---|---|---|
| Score | ||
| Fluency | ||
| Helpfulness | ||
| Truthfulness |
Data credits: LMArena, CC BY 4.0 (licence) · RMT-team, Kuratov et al. Official v0 numeric CSV; results licence not separately stated. · CodeElo (Qwen). Aggregate scores from the official results file; no results licence asserted. The evaluation scaffold agreement is not presented as a licence for these scores · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Stanford HELM (Stanford CRFM); scenario scores from Capabilities, Safety, Long Context, MedHELM, AIR-Bench, MMLU and Finance · EvalPlus Leaderboard and EvalPerf (evalplus.github.io), Apache-2.0; EvalPerf win-rate fractions converted to percentages (licence) · pfgen-bench, Preferred Networks. Apache-2.0 except LLM-generated outputs; aggregate scores only. (licence) · NVIDIA RULER, Hsieh et al. Official README numeric table; no separate results licence asserted. · SeaExam and SeaBench leaderboard, SeaLLMs (DAMO-NLP-SG). Published leaderboard scores; results licence not stated. · WildBench, Allen Institute for AI
docs.api.nvidia.com
ai.azure.com
ai.azure.com
build.nvidia.com
build.nvidia.com
build.nvidia.com
huggingface.co
huggingface.co
huggingface.co
huggingface.co
Also known as: anyscale/mistralai/mixtral-8x7b-instruct-v0.1, bedrock/ap-south-1/mistral.mixtral-8x7b-instruct-v0:1, bedrock/ap-southeast-2/mistral.mixtral-8x7b-instruct-v0:1, bedrock/ca-central-1/mistral.mixtral-8x7b-instruct-v0:1, bedrock/eu-west-1/mistral.mixtral-8x7b-instruct-v0:1, bedrock/eu-west-2/mistral.mixtral-8x7b-instruct-v0:1, bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1, bedrock/sa-east-1/mistral.mixtral-8x7b-instruct-v0:1, bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1, bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1, deepinfra/mistralai/mixtral-8x7b-instruct-v0.1, mistral.mixtral-8x7b-instruct-v0:1, mistralai/mixtral-8x7b-instruct-v0.1, mixtral-8x7b-instruct-v01, nim/mistralai/mixtral-8x7b-instruct-v01, ollama/mixtral-8x7b-instruct-v0.1, ovhcloud/mixtral-8x7b-instruct-v0.1, replicate/mistralai/mixtral-8x7b-instruct-v0.1, together_ai/mistralai/mixtral-8x7b-instruct-v0.1
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works