Claim · coding

o3 (2025-04-16)on Aider Polyglot

76.9 to 81.3 the range across every scoreable measurement we hold

4.4 points between the highest and the lowest

76.9 the number the board uses: the lower median, a real row with its own provenance

3 declared configurations, from 2 runners

0 / 3 rows whose cited page still shows this figure, refetched and checked by us

2 independent runners have measured this, which is rare: on this snapshot only 12 of 321 claim pages can say it.

3 of 3 cited pages no longer show the figure we publish. The page was refetched and split at its own structural boundaries, and no block that names this model carries this number. That does not make the measurement wrong: a leaderboard is a living page and a figure recorded when it was there can be gone by the time you follow the link. It does mean the citation, as printed, no longer supports the number, and this is the only place we know of that says so about its own sources.

Every measurement

3 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.

Score	Provenance	Configuration	Who ran it	Where to check it
81.3 / 100 as published: 81.3%	INDEPENDENT counts toward the ranking	harness diff effort high	aider.chat via Epoch AI 2025-06-25 CC-BY-4.0	checked: this figure is not on the page today2026-08-30 https://aider.chat/docs/leaderboards/
76.9 / 100 as published: 76.9%	INDEPENDENT counts toward the ranking	harness diff effort medium	Aider LLM Leaderboards via Epoch AI CC-BY-4.0	checked: this figure is not on the page today2026-08-30 Aider LLM Leaderboards
76.9 / 100 as published: 76.9%	INDEPENDENT counts toward the ranking	harness diff	aider.chat via Epoch AI 2025-06-25 CC-BY-4.0	checked: this figure is not on the page today2026-08-30 leaderboard row

← 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.