Mistral 7B Instruct v0.2
Dec 2023
Mistral 7B Instruct v0.2Compare inon
Benchmarks of Mistral 7B Instruct v0.214
BenchmarkByScoreRank
Legacy · saturated or no longer reported1
No benchmark matches
Ranking?
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperGemma 3 4BunstatedOpenwins 73%-23%$0.04 / $0.05
BetterGPT-5 Minihighwins 78%+1,150%$0.053OpenGemma 3 12Bunstatedwins 79%+14%$0.05 / $0.10Memory (4-bit): 3.6 GB → 6.1 GBCheaperGemma 2 9B ItOpenwins 71%-32%$0.03 / $0.06Context: 33K → 8K+1CheaperGPT OSS 20BunstatedOpenwins 69%-35%$0.018 / $0.09Memory (4-bit): 3.6 GB → 13 GB+1ModelScoreCostPer taskWhat changes
Gemma 3 4BunstatedOpenwins 73%-23%$0.04 / $0.05Gemma 2 9B ItOpenwins 71%-32%$0.03 / $0.06Context: 33K → 8K+1GPT OSS 20BunstatedOpenwins 69%-35%$0.018 / $0.09Memory (4-bit): 3.6 GB → 13 GB+1
Llama 3.1 8B InstructunstatedOpenwins 60%-55%$0.02 / $0.04Memory (4-bit): 3.6 GB → 4 GB+1Llama 3.2 3B InstructunstatedOpenwins 56%-64%$0.02 / $0.02ModelScoreCostPer taskWhat changes
GPT-5 Minihighwins 78%+1,150%$0.053GPT-6 Lunamaxwins 85%+264%$0.068Function calling only with none · Chat Completions+3GPT-5.6 Lunaxhighwins 85%+718%$0.085GPT-5.6 Terraxhighwins 87%+8,082%$0.63Prompts with >272K input tokensGPT-6.1 Solmaxwins 88%+7,173%$0.72Remove unsupported parameters+5ModelScoreCostPer taskWhat changes
Gemma 3 12BunstatedOpenwins 79%+14%$0.05 / $0.10Memory (4-bit): 3.6 GB → 6.1 GBGemma 3n E4B InstructunstatedOpenwins 75%——Context: 33K → 32K+2
NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4Openwins 74%——Memory (4-bit): 3.6 GB → 11 GBGemma 3 4BunstatedOpenwins 73%-23%$0.04 / $0.05
Granite 4.1 8BunstatedOpenwins 71%——Memory (4-bit): 3.6 GB → 4.4 GBModelScoreCostPer taskWhat changes
Mistral Medium 3.5unstatedOpenwins 85%—$1.50 / $7.50Memory (4-bit): 3.6 GB → 77 GBMistral Large 3unstatedOpenwins 83%—$0.50 / $1.50Memory (4-bit): not verifiedMistral Large 4unstatedwins 82%—$1.36 / $4.18Infinite whitespace stream+4Mistral Largeunstatedwins 73%—$2 / $6Mistral Small 3.1 24BunstatedOpenwins 72%—$0.35 / $0.56Memory (4-bit): 3.6 GB → 14 GB+1Mistral Small 3unstatedOpenwins 67%—$0.05 / $0.08Context: 33K → 32K+2Mixtral 8x22B InstructunstatedOpenwins 62%—$2 / $6Memory (4-bit): 3.6 GB → 84 GBMixtral 8x7B Instruct v0.1Openwins 58%—$0.54 / $0.54Memory (4-bit): 3.6 GB → 28 GBAll Mistral models →Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · 8-bit✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use
History
4 versionsBenchmarks
all categoriesChat & Knowledge
Arena Text · overall1,150#190
Arena Text · Chinese1,009.3#179
Arena Text · English1,133.4#180
Arena Text · French1,036.9#148
Arena Text · German987.3#153
Arena Text · instruction following1,059.9#181
Arena Text · Japanese878#138
Arena Text · non-English1,011.8#183
Arena Text · Russian1,018.2#181
Arena Text · Spanish1,026.2#155
Arena Text · overall · full cohort1,089.5#182
MMLU-Pro · official board30.8#30
Writing & Language
Arena Text · creative writing1,104#188
Arena Text · creative writing · full cohort1,067.5#180
FAQ
How much does Mistral 7B Instruct v0.2 cost?›
$0.055 per 1M input tokens and $0.055 per 1M output tokens (cheapest host: DeepInfra).
Is Mistral 7B Instruct v0.2 free to use?›
There is no free API; the cheapest paid price is $0.055 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Mistral 7B Instruct v0.2, and what is it best at?›
#190 of 196 in Chat & Knowledge, #188 of 195 in Writing & Language.
Is Mistral 7B Instruct v0.2 better than QwQ 32B Preview?›
On Arena Text · creative writing, Mistral 7B Instruct v0.2 scores 1,104 vs 1,104 — about the same.
How can I use Mistral 7B Instruct v0.2?›
Through the API of DeepInfra.
What is the context window of Mistral 7B Instruct v0.2?›
33K tokens.
When was Mistral 7B Instruct v0.2 released? Is there a newer version?›
Released 2023-12-11. It is the current version in its line.
Is Mistral 7B Instruct v0.2 open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Mistral 7B Instruct v0.2 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Mistral 7B Instruct v0.2 read images?›
It accepts text and PDF files as input.
What is Mistral 7B Instruct v0.2?›
Mistral 7B Instruct v0.2 is an open-weights language model from Mistral, released Dec 2023.
What are the best alternatives to Mistral 7B Instruct v0.2?›
Gemma 3 4B (cheaper), GPT-5 Mini (better), Gemma 3 12B (open weights).