Microsoft · model passport
Wizardlm 13b
wizardlm-13b- Open weights
- Llama 2 Community licence
- Released 2023-05-09(curated)
- Overall · LMArena
- 1,150#357 of 396
- Best percentile
- 10.1Overall
- Cohort standing
- 26.0median 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
- 5.8 pct — Hard prompts (1,115)
- 5.9 pct — Coding (1,152)
- 10.1 pct — Instruction following (1,124)
Uneven: 4.3 percentile points between its best and worst axis — 10.1 pct on Overall versus 5.8 pct on Hard prompts.
- Overall10.1 pct1,150Verify →
- Instruction following10.1 pct1,124Verify →
- Coding5.9 pct1,152Verify →
- Hard prompts5.8 pct1,115Verify →
- 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.
wizardlm-13b stands at 26 (raw mean 8) — measured on 4 of 27 axes.
wizardlm-13b stands at 26 versus a cohort median of 24.1 across 35 models released within 180 days — above the peer median.
wizardlm-13b scores at percentile 5.8 on Hard prompts.
wizardlm-13b scores at percentile 5.9 on Coding.
wizardlm-13b ranks between #373 and #781 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 →