MCTS Refine 7B: benchmark scores, price and ranking
MCTS Refine 7B ranks #496 of 743 LLMs on the LLMs Tiger aggregate benchmark score (46.7), based on 2 benchmark results captured up to 2026-10-13.
- Type
- Frontier model
- Open weights
- No
- Aggregate rank
- #496 of 743 (score 46.7)
Across the 2 benchmarks where at least ten models are scored, MCTS Refine 7B is in the top 10% on 0 and in the top half on 0.
MCTS Refine 7B benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| SWE-bench Lite | 16.3% | #15 of 20 | SWE-bench Lite leaderboard | 2026-10-13 |
| SWE-bench Verified | 23.2% | #64 of 73 | SWE-bench Verified leaderboard | 2026-10-13 |
About MCTS Refine 7B
MCTS Refine 7B is a frontier model. No API price is listed for it yet. We hold 2 benchmark results for it across 1 area, and none is in the top tenth of its board.
Where MCTS Refine 7B stands
On our aggregate score, MCTS Refine 7B is #496 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 33% of the ranked field.
MCTS Refine 7B, benchmark by benchmark
MCTS Refine 7B lands below the middle on SWE-bench Lite: 16.3%, #15 of 20, with 70% of the field scoring higher. Claude 4 Sonnet leads at 56.7%; the closest result above is GPT-4 (1106) at 18.0%. It covers real GitHub issues resolved. The board median is 24.7%, so MCTS Refine 7B is 8.3 points below it. Source: SWE-bench Lite leaderboard, captured 2026-10-13.
SWE-bench Verified is a weak spot. MCTS Refine 7B scores 23.2%, #64 of 73, behind 86% 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 MCTS Refine 7B is 33.2 points below it. Source: SWE-bench Verified leaderboard, captured 2026-10-13.
Strengths and weaknesses
Software engineering: weak, ahead of 19% of the field on average across 2 benchmarks. Its best board here is SWE-bench Lite (#15 of 20) and its weakest is SWE-bench Verified (#64 of 73).
Reading these numbers
The 2 scores on this page come from 2 sources: SWE-bench Lite leaderboard (1), SWE-bench Verified leaderboard (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 2 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #493 mistral-small-2402 (46.7)
- #494 mimo-v2.5 (46.7)
- #495 Claude Sonnet 3.5 (46.7)
- #497 Composer 2.5 (46.6)
- #498 gemini-2.0-flash-lite (46.6)
- #499 Mellum2-12B-A2.5B-Thinking-SFT (46.6)
Compare it on the live leaderboard → · How the aggregate score works