Claim · coding

Qwen2.5 Coder 32B Instructon Aider Polyglot

8.0 to 16.4 the range across every scoreable measurement we hold
8.4 points between the highest and the lowest
8.0 the number the board uses: the lower median, a real row with its own provenance
2 declared configurations, from 1 runner
2 / 2 rows whose cited page still shows this figure, refetched and checked by us

All 2 scoreable measurements here come from ONE runner, so this is not a reconciliation and is not presented as one. What it shows is how far a single runner's number moves when the model is run differently.

Every measurement

2 rows. Best first. the board takes the LOWER MEDIAN of the scoreable measurements, which is a real row with its own interval and provenance rather than an interpolated average. a vendor self-report is shown beside the independent numbers and is never one of them; it cannot move a rank.

ScoreProvenanceConfigurationWho ran itWhere to check it
16.4 / 100
as published: 16.4%
INDEPENDENT
counts toward the ranking
Qwen2.5-Coder-32B-Instruct
harness whole
Aider LLM Leaderboards
via Epoch AI
CC-BY-4.0
checked: this figure appears in the page’s row for this model2026-08-3016.4% | aider --model openai/Qwen2.5-Coder-32B-Instruct | 99.6% | whole
Aider LLM Leaderboards
8.0 / 100
as published: 8.0%
INDEPENDENT
counts toward the ranking
Qwen2.5-Coder-32B-Instruct
harness diff
Aider LLM Leaderboards
via Epoch AI
CC-BY-4.0
checked: this figure appears in the page’s row for this model2026-08-308.0% | aider --model openai/Qwen/Qwen2.5-Coder-32B-Instruct # via hyperbolic | 71.6% | diff
Aider LLM Leaderboards
← The Forge Rankings

Snapshot 2026-08-30-62e4e85f043b, manifest dc46131315046f1e, as of 2026-08-30. where only one party has measured a model on a benchmark, this page says so rather than presenting a single number as a reconciliation.