Claim · coding

GPT-5.6 Solon DeepSWE

45.4 to 72.7 the range across every scoreable measurement we hold
27.3 points between the highest and the lowest
69.4 the number the board uses: the lower median, a real row with its own provenance
5 declared configurations, from 1 runner
5 / 5 rows whose cited page still shows this figure, refetched and checked by us

All 5 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

5 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
72.7 / 100
as published: 72.7%
INDEPENDENT
counts toward the ranking
gpt-5.6-sol
harness mini-swe-agent
effort max
deepswe.datacurve.ai
via Epoch AI
CC-BY-4.0
checked: this figure appears in the page’s row for this model2026-08-30model:"gpt-5-6-sol",harness:"mini-swe-agent",reasoning_effort:"max",config:"mini_swe_agent_gpt_5_6_sol_max",source:"deep-swe",pass_rate:0.7266666666666667,pass_
the leaderboard this came from
the leaderboard for this benchmark, not a link to this row
70.7 / 100
as published: 70.7%
INDEPENDENT
counts toward the ranking
gpt-5.6-sol
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:"gpt-5-6-sol",harness:"mini-swe-agent",reasoning_effort:"xhigh",config:"mini_swe_agent_gpt_5_6_sol_xhigh",source:"deep-swe",pass_rate:0.7073170731707317,p
the leaderboard this came from
the leaderboard for this benchmark, not a link to this row
69.4 / 100
as published: 69.4%
INDEPENDENT
counts toward the ranking
gpt-5.6-sol
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:"gpt-5-6-sol",harness:"mini-swe-agent",reasoning_effort:"high",config:"mini_swe_agent_gpt_5_6_sol_high",source:"deep-swe",pass_rate:0.6940133037694013,pas
the leaderboard this came from
the leaderboard for this benchmark, not a link to this row
61.1 / 100
as published: 61.1%
INDEPENDENT
counts toward the ranking
gpt-5.6-sol
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:"gpt-5-6-sol",harness:"mini-swe-agent",reasoning_effort:"medium",config:"mini_swe_agent_gpt_5_6_sol_medium",source:"deep-swe",pass_rate:0.6106194690265486
the leaderboard this came from
the leaderboard for this benchmark, not a link to this row
45.4 / 100
as published: 45.4%
INDEPENDENT
counts toward the ranking
gpt-5.6-sol
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:"gpt-5-6-sol",harness:"mini-swe-agent",reasoning_effort:"low",config:"mini_swe_agent_gpt_5_6_sol_low",source:"deep-swe",pass_rate:0.45353982300884954,pass
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.