claude-opus-4-8-3-trials-72-tasks | terminal-bench-science/terminal-bench-science | 216/216 (7 retries) | Allen | 1 | 8/24/26 |
gpt-5.6-luna-terminal-bench-science-v0.1-curated-trial-2 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 7 | 8/24/26 |
gpt-5.6-luna-terminal-bench-science-v0.1-curated-trial-1 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 9 | 8/24/26 |
gpt-5-6-luna-3-trials-72-tasks | terminal-bench-science/terminal-bench-science | 216/216 (4 retries) | Allen | 24 | 8/24/26 |
glm-5-3-3-trials-72-tasks | terminal-bench-science/terminal-bench-science | 216/216 (6 retries) | Allen | 24 | 8/24/26 |
claude-opus-5-1-trial-reactor-safety-control-infra-rerun | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 0 | 8/24/26 |
claude-fable-5-1-trial-4-task-infra-reruns | terminal-bench-science/terminal-bench-science | 4/4 (1 retry) | Allen | 0 | 8/24/26 |
gpt-5-6-sol-1-trial-1-task-traffic-flux-inversion-rerun | terminal-bench-science/traffic-flux-inversion | 1/1 | Allen | 0 | 8/24/26 |
gpt-5.6-terra-terminal-bench-science-v0.1-curated-trial-3 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 1 | 8/24/26 |
kimi-k3-terminal-bench-science-v0.1-curated-trial-3 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 8 | 8/24/26 |
kimi-k3-terminal-bench-science-v0.1-curated-trial-2 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 13 | 8/24/26 |
kimi-k3-2-trials-72-tasks | terminal-bench-science/terminal-bench-science | 144/144 (67 retries) | Allen | 29 | 8/24/26 |
gpt-5.6-terra-terminal-bench-science-v0.1-curated-trial-2 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 1 | 8/24/26 |
gpt-5.6-terra-terminal-bench-science-v0.1-curated-trial-1 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 4 | 8/24/26 |
gpt-5-6-terra-3-trials-72-tasks | terminal-bench-science/terminal-bench-science | 216/216 (2 retries) | Allen | 6 | 8/24/26 |
gpt-5-6-sol-1-trial-1-task-symbolic-regression-rerun | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 0 | 8/24/26 |
minimax-m3-1-trial-3-tasks-rerun | terminal-bench-science/terminal-bench-science | 3/3 | Allen | 1 | 8/24/26 |
glm-5-3-1-trial-1-task-genomic-model-ranking-key-mapping-smoke | terminal-bench-science/terminal-bench-science | 1/1 (6 retries) | Allen | 0 | 8/24/26 |
glm-5-3-1-trial-1-task-genomic-model-ranking-smoke | terminal-bench-science/terminal-bench-science | 1/1 (4 retries) | Allen | 0 | 8/24/26 |
grok-4.6-v0.1-redacted-localized-sspd-trial-1 | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 0 | 8/24/26 |
grok-4.6-terminal-bench-science-v0.1-curated-trial-3 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 1 | 8/24/26 |
grok-4-6-1-trial-72-tasks | terminal-bench-science/terminal-bench-science | 72/72 (1 retry) | Allen | 1 | 8/24/26 |
claude-opus-5-1-trial-linked-cell-suppression-replacement | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 0 | 8/23/26 |
claude-fable-5-terminal-bench-science-v0.1-curated-trial-3 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 1 | 8/23/26 |
claude-fable-5-terminal-bench-science-v0.1-curated-trial-2 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 1 | 8/23/26 |
claude-opus-5-terminal-bench-science-v0.1-curated-trial-3 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 1 | 8/23/26 |
claude-opus-5-terminal-bench-science-v0.1-curated-trial-2 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 2 | 8/23/26 |
grok-4.6-terminal-bench-science-v0.1-curated-trial-2 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 1 | 8/23/26 |
grok-4.6-terminal-bench-science-v0.1-curated-trial-1 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 1 | 8/23/26 |
gpt-5.6-sol-terminal-bench-science-v0.1-curated-trial-3 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 0 | 8/23/26 |
gpt-5.6-sol-terminal-bench-science-v0.1-curated-trial-2 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 3 | 8/23/26 |
minimax-m3-2-trials-72-tasks | terminal-bench-science/terminal-bench-science | 144/144 (1 retry) | Allen | 4 | 8/23/26 |
claude-fable-5-2-trials-72-tasks | terminal-bench-science/terminal-bench-science | 144/144 (7 retries) | Allen | 5 | 8/23/26 |
claude-opus-5-2-trials-72-tasks | terminal-bench-science/terminal-bench-science | 144/144 (18 retries) | Allen | 4 | 8/23/26 |
grok-4-6-2-trials-72-tasks | terminal-bench-science/terminal-bench-science | 144/144 | Allen | 2 | 8/23/26 |
gpt-5-6-sol-2-trials-72-tasks | terminal-bench-science/terminal-bench-science | 144/144 (2 retries) | Allen | 4 | 8/23/26 |
grok-4-6-1-trials-72-tasks | terminal-bench-science/terminal-bench-science | 72/72 | Allen | 2 | 8/23/26 |
grok-4-6-1-trial-1-task-smoke | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 0 | 8/23/26 |
claude-fable-5-terminal-bench-science-v0.1-curated-trial-1 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 1 | 8/23/26 |
claude-fable-5-1-trials-72-tasks | terminal-bench-science/terminal-bench-science | 72/72 | Allen | 2 | 8/23/26 |
kimi-k3-terminal-bench-science-v0.1-curated-trial-1 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 13 | 8/23/26 |
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 |