Benchmark the finalists on all eight tasks, and archive older results #55

Merged

dongar merged 1 commits from bench-results-harder-tasks into main

2026-09-28 12:41:49 +00:00

Author	SHA1	Message	Date
dongarandClaude Opus 5.5	4b6c48cc96	Benchmark the finalists on all eight tasks, and archive older results CI / checks (push) Skipped CI / checks (pull_request) Successful in 1m12s Details Five runs per task at 320 W with max_turns 40, after the fixes in #50-#52, for qwen3.8-27b, qwen3.6-35b-a3b, gemma-4-26b-a4b, devstral-small-2-24b and mimo-v2.6-9b; the harder four also for claude-haiku-4-5 as the ceiling, and two calibration runs each for local-fast as the floor. Runs failed by the proxy's rate limiter were set aside, not stored. Earlier results move to bench/results/archive/, which the report does not read: they were made at other power caps, at max_turns 24, or on the RTX 4070, and are kept as the record. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>	2026-09-28 03:14:40 +00:00

Author

SHA1

Message

Date

dongarandClaude Opus 5.5

4b6c48cc96

Benchmark the finalists on all eight tasks, and archive older results

CI / checks (push) Skipped

CI / checks (pull_request) Successful in 1m12s

Details

Five runs per task at 320 W with max_turns 40, after the fixes in
#50-#52, for qwen3.8-27b, qwen3.6-35b-a3b, gemma-4-26b-a4b,
devstral-small-2-24b and mimo-v2.6-9b; the harder four also for
claude-haiku-4-5 as the ceiling, and two calibration runs each for
local-fast as the floor. Runs failed by the proxy's rate limiter were
set aside, not stored.

Earlier results move to bench/results/archive/, which the report does
not read: they were made at other power caps, at max_turns 24, or on
the RTX 4070, and are kept as the record.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

2026-09-28 03:14:40 +00:00