deepseek-v4-pro-codex-max-1-trial-genomic-model-ranking-smoke | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 0 | 9/2/26 |
deepseek-v4-pro-codex-max-1-trial-genomic-model-ranking-smoke | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 1 | 9/2/26 |
gemini-3-8-flash-antigravity-1-trial-genomic-model-ranking-smoke | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 1 | 9/2/26 |
gemini-3-7-flash-antigravity-1-trial-genomic-model-ranking-smoke | terminal-bench-science/terminal-bench-science | 1/1 (1 retry) | Allen | 1 | 9/2/26 |
oracle-1-trial-genomic-model-ranking-workspace-smoke | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 0 | 9/2/26 |
gemini-3-7-flash-3-trials-70-tasks | terminal-bench-science/terminal-bench-science | 210/210 (32 retries) | Allen | 0 | 8/30/26 |
glm-5-3-flash-3-trials-70-tasks-claude-code | terminal-bench-science/terminal-bench-science | 210/210 (3 retries) | Allen | 32 | 8/30/26 |
glm-5-3-cc-recovered-final-three | 2a1abd12a6bb69c17f5af312b88f3029de3fcd9ba366808d1335a15ba458cef1 +2 more | 3/3 | Allen | 0 | 8/26/26 |
glm-5-3-cc-modal-localized-sspd-solver-replacement-primary | terminal-bench-science/terminal-bench-science | 0/1 | Allen | 0 | 8/26/26 |
glm-5-3-cc-modal-foraging-cognitive-model-replacement-primary | terminal-bench-science/terminal-bench-science | 0/1 | Allen | 0 | 8/26/26 |
glm-5-3-cc-modal-tamp-skill-planning-replacement-primary | terminal-bench-science/terminal-bench-science | 0/1 | Allen | 0 | 8/26/26 |
glm-5-3-cc-modal-microarch-modeling-replacement-primary | terminal-bench-science/terminal-bench-science | 1/1 (1 retry) | Allen | 1 | 8/26/26 |
kimi-k3-modal-protein-active-learning-replacement-primary | terminal-bench-science/terminal-bench-science | 0/1 | Allen | 0 | 8/26/26 |
kimi-k3-modal-noisy-blackbox-optimization-replacement-primary | terminal-bench-science/terminal-bench-science | 0/1 | Allen | 0 | 8/26/26 |
kimi-k3-modal-hbv-calibration-1-replacement-primary | terminal-bench-science/terminal-bench-science | 0/1 | Allen | 0 | 8/26/26 |
kimi-k3-modal-baseline-free-localization-replacement-primary | terminal-bench-science/terminal-bench-science | 0/1 | Allen | 0 | 8/26/26 |
glm-5-3-cc-modal-protein-active-learning-replacement-primary | terminal-bench-science/terminal-bench-science | 1/1 (2 retries) | Allen | 1 | 8/26/26 |
kimi-k3-modal-1-trial-71-tasks-third-corrected | terminal-bench-science/terminal-bench-science | 43/71 (19 retries) | Allen | 37 | 8/26/26 |
kimi-k3-modal-eeg-erp-recovery-replacement-primary | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 0 | 8/26/26 |
kimi-k3-modal-1-trial-71-tasks-third | terminal-bench-science/terminal-bench-science | 71/71 (48 retries) | Allen | 71 | 8/26/26 |
glm-5-3-cc-modal-1-trial-71-tasks-third | terminal-bench-science/terminal-bench-science | 15/71 (4 retries) | Allen | 11 | 8/26/26 |
glm-5-3-cc-modal-eeg-erp-recovery-primary | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 1 | 8/26/26 |
glm-5-3-cc-modal-eeg-erp-recovery-backup | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 0 | 8/26/26 |
kimi-k3-modal-eeg-erp-recovery-backup | terminal-bench-science/terminal-bench-science | 1/1 (2 retries) | Allen | 1 | 8/26/26 |
glm-5-3-cc-modal-tamp-skill-planning-primary | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 1 | 8/26/26 |
glm-5-3-cc-modal-tamp-skill-planning-backup | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 0 | 8/26/26 |
kimi-k3-modal-eeg-erp-recovery-primary | terminal-bench-science/terminal-bench-science | 1/1 (2 retries) | Allen | 1 | 8/26/26 |
glm-5-3-claude-code-2-trials-2-tasks-replacements | terminal-bench-science/terminal-bench-science | 4/4 (4 retries) | Allen | 0 | 8/26/26 |
kimi-regwise-2-trials-2-tasks-replacements | terminal-bench-science/terminal-bench-science | 4/4 (4 retries) | Allen | 0 | 8/26/26 |
kimi-regwise-2-trials-72-tasks | terminal-bench-science/terminal-bench-science | 144/144 (72 retries) | Allen | 9 | 8/25/26 |
regwise-1-trial-genomic-model-ranking-smoke | terminal-bench-science/genomic-model-ranking | 1/1 | Allen | 0 | 8/25/26 |
glm-5-3-opencode-1-trial-stereo-dem-icesat2-row-fill | terminal-bench-science/stereo-dem-icesat2 | 1/1 | Allen | 0 | 8/25/26 |
glm-5.3-terminal-bench-science-v0.1-curated-trial-3 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 2 | 8/25/26 |
glm-5.3-terminal-bench-science-v0.1-curated-trial-2 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 2 | 8/25/26 |
glm-5.3-terminal-bench-science-v0.1-curated-trial-1 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 0 | 8/25/26 |
glm-5-3-3-trials-72-tasks-claude-code-v2 | terminal-bench-science/terminal-bench-science | 216/216 (16 retries) | Allen | 5 | 8/25/26 |
glm-5-3-1-trial-cell-lineage-idle-timeout-fix-smoke | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 0 | 8/25/26 |
glm-5-3-1-trial-cell-lineage-retry-policy-smoke | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 0 | 8/25/26 |
glm-5-3-opencode-1-trial-traffic-flux-inversion-infra-retry | terminal-bench-science/traffic-flux-inversion | 1/1 | Allen | 1 | 8/25/26 |
glm-5-3-opencode-2-trials-stereo-dem-icesat2-stall-retries | terminal-bench-science/stereo-dem-icesat2 | 2/2 | Allen | 2 | 8/25/26 |
glm-5-3-claude-code-3-trials-72-tasks | terminal-bench-science/terminal-bench-science | 216/216 | Allen | 1 | 8/25/26 |
gemini-3-7-flash-3-trials-72-tasks | terminal-bench-science/terminal-bench-science | 216/216 (8 retries) | Allen | 37 | 8/25/26 |
gemini-3-7-flash-1-trial-genomic-model-ranking-shared-secret-smoke | terminal-bench-science/genomic-model-ranking | 1/1 | Allen | 0 | 8/25/26 |
glm-5-3-1-trial-genomic-model-ranking-explicit-secret-smoke | terminal-bench-science/terminal-bench-science | 1/1 | Allen | 0 | 8/25/26 |
glm-5-3-1-trial-genomic-model-ranking-auth-token-smoke | terminal-bench-science/terminal-bench-science | 1/1 (4 retries) | Allen | 0 | 8/25/26 |
glm-5-3-3-trials-72-tasks-claude-code | terminal-bench-science/terminal-bench-science | 216/216 (32 retries) | Allen | 0 | 8/25/26 |
claude-opus-4.8-terminal-bench-science-v0.1-curated-trial-3 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 1 | 8/24/26 |
gpt-5.6-luna-terminal-bench-science-v0.1-curated-trial-3 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 6 | 8/24/26 |
claude-opus-4.8-terminal-bench-science-v0.1-curated-trial-2 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 0 | 8/24/26 |
claude-opus-4.8-terminal-bench-science-v0.1-curated-trial-1 | terminal-bench-science/terminal-bench-science | 70/70 | Allen | 0 | 8/24/26 |