Claim · coding

Grok 4.6on DeepSWE

41.6 to 67.5 the range across every scoreable measurement we hold
25.8 points between the highest and the lowest
65.2 the number the board uses: the lower median, a real row with its own provenance
4 declared configurations, from 1 runner
4 / 4 rows whose cited page still shows this figure, refetched and checked by us

All 4 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

4 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
67.5 / 100
as published: 67.5%
INDEPENDENT
counts toward the ranking
grok-4.6
harness mini-swe-agent
effort medium
deepswe.datacurve.ai
via Epoch AI
CC-BY-4.0
checked: this figure appears in the page’s row for this model2026-08-30model:"grok-4-6",harness:"mini-swe-agent",reasoning_effort:"medium",config:"mini_swe_agent_grok_4_6_medium",source:"deep-swe",pass_rate:0.6747787610619469,pass_
the leaderboard this came from
the leaderboard for this benchmark, not a link to this row
66.7 / 100
as published: 66.7%
INDEPENDENT
counts toward the ranking
grok-4.6
harness mini-swe-agent
effort xhigh
deepswe.datacurve.ai
via Epoch AI
CC-BY-4.0
checked: this figure appears in the page’s row for this model2026-08-30model:"grok-4-6",harness:"mini-swe-agent",reasoning_effort:"xhigh",config:"mini_swe_agent_grok_4_6_xhigh",source:"deep-swe",pass_rate:0.6674057649667405,pass_at
the leaderboard this came from
the leaderboard for this benchmark, not a link to this row
65.2 / 100
as published: 65.2%
INDEPENDENT
counts toward the ranking
grok-4.6
harness mini-swe-agent
effort high
deepswe.datacurve.ai
via Epoch AI
CC-BY-4.0
checked: this figure appears in the page’s row for this model2026-08-30model:"grok-4-6",harness:"mini-swe-agent",reasoning_effort:"high",config:"mini_swe_agent_grok_4_6_high",source:"deep-swe",pass_rate:0.6518847006651884,pass_at_1
the leaderboard this came from
the leaderboard for this benchmark, not a link to this row
41.6 / 100
as published: 41.6%
INDEPENDENT
counts toward the ranking
grok-4.6
harness mini-swe-agent
effort low
deepswe.datacurve.ai
via Epoch AI
CC-BY-4.0
checked: this figure appears in the page’s row for this model2026-08-30model:"grok-4-6",harness:"mini-swe-agent",reasoning_effort:"low",config:"mini_swe_agent_grok_4_6_low",source:"deep-swe",pass_rate:0.41648106904231624,pass_at_1:
the leaderboard this came from
the leaderboard for this benchmark, not a link to this 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.