Google · model passport
Gemma 7b It
gemma-7b-it- Open weights
- Gemma license licence
- 8.5B params
- Released 2024-02-21(curated)
- Overall · LMArena
- 1,138#366 of 396
- Best percentile
- 9.8Hard prompts
- Cohort standing
- 26.2median 31.5
What the data says
Benchmarked on 4 of 27 tracked axes. Every figure below is the model's own published result on that board.
Weakest axes
- 7.6 pct — Instruction following (1,105)
- 7.8 pct — Overall (1,138)
- 7.9 pct — Coding (1,167)
Uneven: 2.2 percentile points between its best and worst axis — 9.8 pct on Hard prompts versus 7.6 pct on Instruction following.
- Hard prompts9.8 pct1,154Verify →
- Coding7.9 pct1,167Verify →
- Overall7.8 pct1,138Verify →
- Instruction following7.6 pct1,105Verify →
- 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
- LiveBenchNot 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.
How to run it
Run it yourself
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "google/gemma-7b-it"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)Ollama
We don't sync Ollama tags, so we won't print a command we can't verify — a wrong one would pull the wrong model. Search the Ollama library →
Unsloth fine-tuning recipes are model-specific and we don't derive them here. Unsloth docs →
Identifiers, limits and prices are synced from the upstream source shown above. Any field we haven't synced is left out entirely rather than guessed.
gemma-7b-it stands at 26.2 (raw mean 8.3) — measured on 4 of 27 axes.
gemma-7b-it stands at 26.2 versus a cohort median of 31.5 across 97 models released within 180 days — below the peer median.
gemma-7b-it scores at percentile 7.6 on Instruction following.
gemma-7b-it scores at percentile 7.8 on Overall.
gemma-7b-it ranks between #381 and #803 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 →