whatmodel.sh / OpenHermes 2.5 Mistral 7B

OpenHermes 2.5 Mistral 7B

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

OpenHermes 2.5 Mistral 7B is an open-weights language model from Nous Research, released October 2023. Its published size is 7.24B parameters. Licence: apache-2.0.

Catalogue identity notes

Arena entry 'openhermes-2.5-mistral-7b' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'openhermes-2.5-mistral-7b' as 'OpenHermes-2.5-Mistral-7B' (NousResearch, Apache-2.0), linking https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B. Maker repo teknium/OpenHermes-2.5-Mistral-7B @24c0bea: licence tag apache-2.0. 7,241,748,480 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2023-10: month the maker's Hugging Face repo was created (createdAt 2023-10-29).

39.4±0.9#539 of 719 LLMsfrom 14 benchmark results across 8 sources

$ how it compares

The LLMs ranked either side of OpenHermes 2.5 Mistral 7B, out of 828 with a score, then more from Nous Research.

#modelscorewhereRAMreleased
629LLaVA-v1.6-34B LLaVA40±2local~24GB2024-01
630Bielik 1.5B v3.0 Instruct SpeakLeash40±3local~2.4GB2025-04
631OpenHermes 2.5 Mistral 7B Nous Research39±1local~6.1GB2023-10
632Granite 3.3 2B Instruct IBM39±1local~3GB2025-04
633Phi-3-mini-128k-instruct (Apr 2024) Microsoft39±2local~9.5GB2024-04
more from Nous Research
389Hermes 3 Llama 3.1 405B Nous Research51±1local~114GB2024-08
447Hermes 3 Llama 3.1 70B Nous Research49±1local~44GB2024-07
461Hermes 2 Theta Llama-3 70B Nous Research48±2local~47GB2024-06

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #360 of 458 * · 6.9% of its score · 1 test

Beats LFM2.5 8B-A1B, Qwen3-VL 2B Thinking, DeepSeek R1 Distill Qwen 7B here, though they rank higher overall. Trails Qwen2.5 1.5B Instruct, Phi-3-mini-128k-instruct (Apr 2024) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
HumanEval48.2% ✎▁▁▁▁▁▃▅▅█▃▂▁ beats 75/190easy · avg 77%▇▇▇ 6.9%sharp · at its level · small run
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #332 of 393 · 34% of its score · 3 tests

Beats OpenThinker3 7B, Gemma 4 E2B, Code Llama 70B Instruct here, though they rank higher overall. Trails Granite 4.0 H 350M, LFM2 350M, Gemma 3 1B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
AlpacaEval 2 length-controlled16.3% ✎▁▂▂▃▆▆█▆▄▄▁▁ beats 42/122medium · avg 39%▇▇▇▇▇▇▇ 19%typical
Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024)1075.0 ✎▂▁▂▁▃▇█▆▇▄▂▂ beats 35/95avg 1201▇▇▇ 7.6%blunt
LMArena (text)1175.9 ✎▁▁▁▂▃▃▃▆▆▇█▃ beats 53/379avg 1268▇▇▇ 7.5%blunt
math█··········█ #2 of 2 * · 4.8% of its score · 1 test
testresultvs the others in its rundifficultycountswhy
GSM8K73.5% ✎▂▂▂▅▅▆▅▇█▇▄▃ beats 78/146very easy · avg 89%▇▇ 4.8%sharp · at its level · small run
other tests9 not in a task · 54% of its score
testresultvs the others in its rundifficultycountswhy
LiveBench 2024-07-2624.1% ✎▁▁▁▂▂▃▃█▆▃▅▃ beats 17/61medium · avg 41%▇▇▇▇▇▇▇▇▇ 23%typical
Natural Questions (closed book)26.6% ✎▁·▁·▁▂▁▂·▅▂█ beats 22/28medium · avg 58%▇▇▇▇▇ 13%at its level
BIG-Bench Hard59.9% ✎▁▁▁▁▂▄▅▅█▃▄▁ beats 66/129easy · avg 80%▇▇ 5.1%sharp · at its level · small run
Polish EQ-Bench v2 (SpeakLeash)37.5% ✎▁··▁▁▂▃▆▅▆█▆ beats 11/70medium · avg 64%▇▇ 4.3%at its level
MMLU63.8% ✎▁▁▁▁▁▂▃▅█▃▆▃ beats 80/183easy · avg 77%▇ 3.5%at its level · small run
Open PT-LLM Leaderboard average (9 Portuguese tasks)66.5% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 126/276medium · avg 73%▇ 1.6%at its level · noisy
TriviaQA66.0% ✎▁··▁█▃▃▁▄▅▄█ beats 27/28easy · avg 79%▇ 1.3%at its level · noisy
HaluEval QA hallucination detection (accuracy)50.6% ✎█▁▃·▁▁·▁▁▁▁▁ beats 17/27medium · avg 70%▇ 1.2%sharp · noisy
1 more test
testresultvs the others in its rundifficultycountswhy
TruthfulQA MC253.0% ✎▅▃█▆▁▂▅···▁▁ beats 25/31medium · avg 64%▇ 0.6%blunt · at its level

$ where to run it

llama.cpp · recommended

version

  1. Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
    macOS / Linux
    curl -LsSf https://llama.app/install.sh | sh
    Windows
    irm https://llama.app/install.ps1 | iex

    other ways to install ↗

  2. Run OpenHermes 2.5 Mistral 7B · needs ~4.4 GB · from huggingface.co/TheBloke
    chat in the terminal
    llama cli -hf TheBloke/OpenHermes-2.5-Mistral-7B-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf TheBloke/OpenHermes-2.5-Mistral-7B-GGUF:Q4_K_M

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run OpenHermes 2.5 Mistral 7B · needs ~4.4 GB · from huggingface.co/TheBloke

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run OpenHermes 2.5 Mistral 7B · needs ~4.84 GB · from ollama.com
    chat in the terminal
    ollama run openhermes:7b-mistral-v2.5-q4_K_M

MLX (Mac)

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run OpenHermes 2.5 Mistral 7B · needs ~14.5 GB, Mac only · from huggingface.co/TheBlueObserver
    chat in the terminal
    mlx_lm.chat --model TheBlueObserver/OpenHermes-2.5-Mistral-7B-MLX
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model TheBlueObserver/OpenHermes-2.5-Mistral-7B-MLX

Weights and documentation: huggingface.co/teknium ↗

$ how the score was worked out · LiveBench model judgments (HF… 23%, OpenChat 3.5 model card (open… 20%, AlpacaEval 1.0 and 2.0 leader… 19% and 5 more

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasets1▇▇▇▇▇▇▇ 23%Apache-2.0 (stated in the LiveBench datasheet)
OpenChat 3.5 model card (openchat/openchat_3.5)4▇▇▇▇▇▇ 20%Apache-2.0
AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)1▇▇▇▇▇▇ 19%Apache-2.0
Hallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)4▇▇▇▇▇ 17%Apache-2.0
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)1▇▇ 8%CC-BY-4.0
LMArena leaderboard dataset1▇▇ 8%CC BY 4.0
SpeakLeash Polish EQ-Bench leaderboard1▇ 4%Apache-2.0
Open Portuguese LLM Leaderboard (archived)1▇ 2%Apache-2.0
prior · pull toward the middle▇ 0%
weighted average= 39.4

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json