Llama 4 Maverick Instruct: benchmark scores, price and ranking
Llama 4 Maverick Instruct from Meta ranks #491 of 743 LLMs on the LLMs Tiger aggregate benchmark score (46.7), based on 1 benchmark results captured up to 2026-10-13.
- Organisation
- Meta
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2025-04-05 (source: curated)
- Aggregate rank
- #491 of 743 (score 46.7)
Across the 1 benchmark where at least ten models are scored, Llama 4 Maverick Instruct is in the top 10% on 0 and in the top half on 0.
Llama 4 Maverick Instruct benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| SWE-bench Verified | 21.0% | #66 of 73 | SWE-bench Verified leaderboard | 2026-10-13 |
About Llama 4 Maverick Instruct
Llama 4 Maverick Instruct is an open-weight model that can run on your own hardware from Meta. It was released on 2025-04-05, according to the developer's announcement. No API price is listed for it yet. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.
Where Llama 4 Maverick Instruct stands
On our aggregate score, Llama 4 Maverick Instruct is #491 of 743 ranked models, in the lower half. Its score is 46.7; the scale is centred on 50, so it sits 3.3 points below the typical model. That beats 34% of the ranked field. Among the 6 ranked Meta models it is #3. The next one up is llama3-70b-8192 at 48.1. The next one down is Llama 4 Scout Instruct at 45.6.
Llama 4 Maverick Instruct, benchmark by benchmark
SWE-bench Verified is a weak spot. Llama 4 Maverick Instruct scores 21.0%, #66 of 73, behind 89% of the models measured. The leader, Claude Opus 4.7 (max), reaches 83.5%. It covers real GitHub issues resolved. The board median is 56.4%, so Llama 4 Maverick Instruct is 35.4 points below it. Source: SWE-bench Verified leaderboard, captured 2026-10-13.
Release history
The next one was Llama 4 Scout Instruct on 2025-04-05, at 45.6.
Reading these numbers
The 1 score on this page comes from 1 source: SWE-bench Verified leaderboard (1). 1 of them come from an official leaderboard and 0 from datasets or third-party runs. With 1 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #488 Gemini 2.0 Pro Exp (Feb 2025) (46.7)
- #489 mistral-medium-2312 (46.7)
- #490 grok-4-1-fast-reasoning (46.7)
- #492 internlm2-chat-20b (46.7)
- #493 mistral-small-2402 (46.7)
- #494 mimo-v2.5 (46.7)
More from Meta
- Llama3-SWE-RL-70B (#337, 48.6)
- llama3-70b-8192 (#381, 48.1)
- Llama 4 Scout Instruct (#565, 45.6)
- ollama/llama3.2:3b-instruct-fp16 (#631, 44.5)
- SWE-Llama 7B (#683, 43.2)
Compare it on the live leaderboard → · How the aggregate score works