kimi-k3-1-trials-72-tasks | terminal-bench-science/terminal-bench-science | 72/72 (43 retries) | Allen | 6 | 8/23/26 |
kimi-k3-1-trial-1-task-smoke-retry | terminal-bench-science/genomic-model-ranking | 1/1 (1 retry) | Allen | 0 | 8/23/26 |
kimi-k3-1-trial-1-task-smoke | terminal-bench-science/genomic-model-ranking | 1/1 | Allen | 1 | 8/23/26 |
claude-opus-5-1-trial-1-task-gen-turan-paths-rerun-128k | terminal-bench-science/gen-turan-paths | 1/1 | Allen | 0 | 8/23/26 |
gemini-3-7-flash-1-trials-72-tasks-retry2 | terminal-bench-science/terminal-bench-science | 72/72 (5 retries) | Allen | 54 | 8/23/26 |
gemini-3-7-flash-1-trials-72-tasks-retry | terminal-bench-science/terminal-bench-science | 72/72 | Allen | 1 | 8/23/26 |
gemini-3-7-flash-1-trials-72-tasks | terminal-bench-science/terminal-bench-science | 72/72 | Allen | 10 | 8/23/26 |
minimax-m3-1-trials-72-tasks | terminal-bench-science/terminal-bench-science | 72/72 (1 retry) | Allen | 4 | 8/23/26 |
claude-opus-5-1-trial-1-task-gen-turan-paths-rerun | terminal-bench-science/gen-turan-paths | 1/1 | Allen | 1 | 8/23/26 |
gpt-5.6-sol-1-trial-1-task-noisy-blackbox-rerun | terminal-bench-science/noisy-blackbox-optimization | 1/1 | Allen | 0 | 8/23/26 |
regrade-sol-noisy-blackbox-verifier-timeout | terminal-bench-science/noisy-blackbox-optimization | 1/1 | Allen | 0 | 8/23/26 |
gpt-5-6-sol-1-trials-1-leaky-bloch-meep | terminal-bench-science/leaky-bloch-meep | 1/1 | Allen | 0 | 8/23/26 |
claude-opus-5-1-trials-1-leaky-bloch-meep | terminal-bench-science/leaky-bloch-meep | 1/1 | Allen | 0 | 8/23/26 |
gpt-5-6-sol-1-trials-1-fly-body-tracking | terminal-bench-science/fly-body-tracking | 1/1 | Allen | 0 | 8/23/26 |
claude-opus-5-1-trials-1-fly-body-tracking | terminal-bench-science/fly-body-tracking | 1/1 | Allen | 0 | 8/23/26 |
oracle-fix3-leaky-bloch-meep | terminal-bench-science/leaky-bloch-meep | 1/1 | Allen | 0 | 8/23/26 |
gpt-5-6-sol-1-trials-4-repaired-tasks | terminal-bench-science/finite-free-stam +3 more | 4/4 | Allen | 0 | 8/23/26 |
claude-opus-5-1-trials-4-repaired-tasks | terminal-bench-science/finite-free-stam +3 more | 4/4 | Allen | 0 | 8/23/26 |
oracle-fix-fly-body-tracking | terminal-bench-science/fly-body-tracking | 1/1 | Allen | 0 | 8/23/26 |
oracle-fix4-localized-sspd-solver | terminal-bench-science/localized-sspd-solver | 1/1 | Allen | 0 | 8/23/26 |
oracle-fix2-small-area-equivalence | terminal-bench-science/small-area-equivalence | 1/1 | Allen | 0 | 8/23/26 |
oracle-fix3-localized-sspd-solver | terminal-bench-science/localized-sspd-solver | 1/1 | Allen | 0 | 8/23/26 |
oracle-fix-small-area-equivalence | terminal-bench-science/small-area-equivalence | 1/1 | Allen | 0 | 8/23/26 |
oracle-fix-tamp-skill-planning | terminal-bench-science/tamp-skill-planning | 1/1 | Allen | 0 | 8/23/26 |
oracle-fix2-localized-sspd-solver | terminal-bench-science/localized-sspd-solver | 1/1 | Allen | 0 | 8/23/26 |
oracle-fix2-leaky-bloch-meep | terminal-bench-science/leaky-bloch-meep | 1/1 | Allen | 1 | 8/23/26 |
oracle-diagnostic-fly-body-tracking-4h | terminal-bench-science/fly-body-tracking | 1/1 | Allen | 0 | 8/23/26 |
oracle-fix-localized-sspd-solver | terminal-bench-science/localized-sspd-solver | 1/1 | Allen | 0 | 8/23/26 |
oracle-fix-leaky-bloch-meep | terminal-bench-science/leaky-bloch-meep | 1/1 | Allen | 0 | 8/23/26 |
oracle-diagnostic-tamp-skill-planning | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 1 | 8/23/26 |
oracle-diagnostic-finite-free-stam | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 0 | 8/23/26 |
oracle-diagnostic-fly-body-tracking | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 1 | 8/23/26 |
oracle-diagnostic-small-area-equivalence | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 0 | 8/23/26 |
oracle-diagnostic-localized-sspd-solver | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 0 | 8/23/26 |
oracle-diagnostic-leaky-bloch-meep | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 0 | 8/23/26 |
gpt-5.6-sol-terminal-bench-science-v0.1-curated-trial-1 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 1 | 8/23/26 |
claude-opus-5-terminal-bench-science-v0.1-curated-trial-1 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 0 | 8/23/26 |
gpt-5-6-sol-1-trials-66-tasks | terminal-bench-science/terminal-bench-science | 66/66 | Allen | 2 | 8/23/26 |
gemini-3-7-flash-1-trials-66-tasks | terminal-bench-science/terminal-bench-science | 66/66 | Allen | 15 | 8/23/26 |
claude-opus-5-1-trials-66-tasks | terminal-bench-science/terminal-bench-science | 66/66 | Allen | 2 | 8/23/26 |
minimax-m3-1-trials-1-tasks | allengrahamhart/terminal-bench-science-v0-1 | 1/1 | Allen | 0 | 8/23/26 |
k3-1-trials-1-tasks-retry-1 | allengrahamhart/terminal-bench-science-v0-1 | 1/1 (4 retries) | Allen | 0 | 8/23/26 |
minimax-m2-7-1-trials-1-tasks-retry-1 | allengrahamhart/terminal-bench-science-v0-1 | 1/1 | Allen | 1 | 8/23/26 |
claude-opus-5-1-trials-1-tasks | allengrahamhart/terminal-bench-science-v0-1 | 1/1 | Allen | 1 | 8/23/26 |
k3-1-trials-1-tasks | allengrahamhart/terminal-bench-science-v0-1 | 1/1 | Allen | 1 | 8/23/26 |
minimax-m2-7-1-trials-1-tasks | allengrahamhart/terminal-bench-science-v0-1 | 1/1 | Allen | 1 | 8/23/26 |
claude-opus-5-1-trials-1-tasks | allengrahamhart/terminal-bench-science-v0-1 | 1/1 | Allen | 1 | 8/23/26 |
gpt-5.6-sol-1-trials-1-tasks | allengrahamhart/terminal-bench-science-v0-1 | 1/1 | Allen | 0 | 8/23/26 |
gpt-5.6-sol-1-trials-1-tasks | allengrahamhart/terminal-bench-science-v0-1 | 1/1 | Allen | 0 | 8/23/26 |
claude-opus-5-1-trials-1-tasks | allengrahamhart/terminal-bench-science-v0-1 | 1/1 | Allen | 0 | 8/23/26 |