Model passport
Mpt 30b Chat
mpt-30b-chat- Open weights
- CC-BY-NC-SA-4.0 licence
- Released 2023-06-22(curated)
- Overall · LMArena
- 1,151#356 of 396
- Best percentile
- 11.9Instruction following
- Cohort standing
- 27.4median 26.0
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
- 8.4 pct — Coding (1,168)
- 10.4 pct — Overall (1,151)
- 10.9 pct — Hard prompts (1,158)
Uneven: 3.5 percentile points between its best and worst axis — 11.9 pct on Instruction following versus 8.4 pct on Coding.
- Instruction following11.9 pct1,135Verify →
- Hard prompts10.9 pct1,158Verify →
- Overall10.4 pct1,151Verify →
- Coding8.4 pct1,168Verify →
- 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.
mpt-30b-chat stands at 27.4 (raw mean 10.4) — measured on 4 of 27 axes.
mpt-30b-chat stands at 27.4 versus a cohort median of 26 across 48 models released within 180 days — above the peer median.
mpt-30b-chat scores at percentile 8.4 on Coding.
mpt-30b-chat scores at percentile 10.4 on Overall.
mpt-30b-chat ranks between #368 and #777 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 →