Meta · model passport
Llama 13b
llama-13b- Open weights
- Non-commercial licence
- Released 2023-02-24(curated)
- Overall · LMArena
- 975#395 of 396
- Best percentile
- 0.5Overall
- Cohort standing
- 21.6median 24.1
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
- 0.3 pct — Hard prompts (919)
- 0.3 pct — Coding (883)
- 0.5 pct — Instruction following (919)
Uneven: 0.2 percentile points between its best and worst axis — 0.5 pct on Overall versus 0.3 pct on Hard prompts.
- Overall0.5 pct975Verify →
- Instruction following0.5 pct919Verify →
- Coding0.3 pct883Verify →
- Hard prompts0.3 pct919Verify →
- 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.
llama-13b stands at 21.6 (raw mean 0.4) — measured on 4 of 27 axes.
llama-13b stands at 21.6 versus a cohort median of 24.1 across 25 models released within 180 days — below the peer median.
llama-13b scores at percentile 0.3 on Coding.
llama-13b scores at percentile 0.3 on Hard prompts.
llama-13b ranks between #410 and #894 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 →