Teknium · model passport
Openhermes 2 5 Mistral 7b
openhermes-2-5-mistral-7b- Open weights
- Apache-2.0 licence
- Released 2023-11-10(curated)
- Overall · LMArena
- 1,176#343 of 396
- Best percentile
- 13.9Hard prompts
- Cohort standing
- 26.2median 28.5
What the data says
Benchmarked on 5 of 27 tracked axes. Every figure below is the model's own published result on that board.
Weakest axes
- 8.2 pct — LiveBench (23.4%)
- 10.5 pct — Coding (1,187)
- 13.6 pct — Instruction following (1,154)
Uneven: 5.7 percentile points between its best and worst axis — 13.9 pct on Hard prompts versus 8.2 pct on LiveBench.
- Hard prompts13.9 pct1,181Verify →
- Overall13.6 pct1,176Verify →
- Instruction following13.6 pct1,154Verify →
- Coding10.5 pct1,187Verify →
- LiveBench8.2 pct23.4%Verify →
- WebDev ArenaNot benchmarked
- Vision ArenaNot benchmarked
- Factuality ArenaNot benchmarked
- Search ArenaNot benchmarked
- Document ArenaNot benchmarked
- Agent ArenaNot benchmarked
- GPQA DiamondNot benchmarked
- AIME (math)Not benchmarked
- FrontierMathNot benchmarked
- SimpleQA VerifiedNot benchmarked
- ARC-AGI-2Not benchmarked
- Humanity's Last ExamNot benchmarked
- SimpleBenchNot benchmarked
- BFCL v4 (function calling)Not benchmarked
- SWE-bench Verified (live board)Not benchmarked
- Terminal-Bench 4.0Not benchmarked
- MMLU-Pro (Artificial Analysis)Not benchmarked
- LiveCodeBench (Artificial Analysis)Not benchmarked
- IFBench (Artificial Analysis)Not benchmarked
- HHEM Hallucination (Vectara)Not benchmarked
- SWE-bench VerifiedNot benchmarked
- Terminal-BenchNot benchmarked
Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.
openhermes-2.5-mistral-7b stands at 26.2 (raw mean 12) — measured on 5 of 27 axes.
openhermes-2.5-mistral-7b stands at 26.2 versus a cohort median of 28.5 across 72 models released within 180 days — below the peer median.
openhermes-2.5-mistral-7b scores at percentile 8.2 on LiveBench.
openhermes-2.5-mistral-7b scores at percentile 10.5 on Coding.
openhermes-2.5-mistral-7b ranks between #358 and #950 across 5 built-in weightings — best under "Conversation-first", worst under "All sources".
Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →