Terminal-Bench

Source-qualified evaluations, report statistics and safety observations.

openai/inkling-small-1102-rc17

MetricValueUnit
Terminal-Bench · accuracy0.1303percent
Terminal-Bench · avg_trial_duration_sec7272.7seconds
Terminal-Bench · pass_at_20.2percent
Terminal-Bench · pass_at_30.2439percent
Terminal-Bench · pass_at_40.2758percent
Terminal-Bench · pass_at_50.303percent
Terminal-Bench · total_cost_usd963.65USD

openrouter/tencent/hy4-preview

MetricValueUnit
Terminal-Bench · accuracy0.19390000000000002percent
Terminal-Bench · avg_trial_duration_sec6967seconds
Terminal-Bench · pass_at_20.2773percent
Terminal-Bench · pass_at_30.3227percent
Terminal-Bench · pass_at_40.3545percent
Terminal-Bench · pass_at_50.3788percent
Terminal-Bench · total_cost_usd658.09USD

openrouter/reflection/beam-1.0-501b-a23b

MetricValueUnit
Terminal-Bench · accuracy0.0636percent
Terminal-Bench · avg_trial_duration_sec178.6seconds
Terminal-Bench · pass_at_20.0879percent
Terminal-Bench · pass_at_30.0985percent
Terminal-Bench · pass_at_40.103percent
Terminal-Bench · pass_at_50.1061percent
Terminal-Bench · total_cost_usd220.96USD

deepseek/deepseek-v4.1-flash-1017

MetricValueUnit
Terminal-Bench · accuracy0.3848percent
Terminal-Bench · avg_trial_duration_sec148.4seconds
Terminal-Bench · pass_at_20.5061percent
Terminal-Bench · pass_at_30.5727percent
Terminal-Bench · pass_at_40.6182percent
Terminal-Bench · pass_at_50.6515percent
Terminal-Bench · total_cost_usd184.89USD

openrouter/deepseek/deepseek-v4-pro-0813

MetricValueUnit
Terminal-Bench · accuracy0.0667percent
Terminal-Bench · avg_trial_duration_sec138.2seconds
Terminal-Bench · pass_at_20.1212percent
Terminal-Bench · pass_at_30.1652percent
Terminal-Bench · pass_at_40.2percent
Terminal-Bench · pass_at_50.2273percent
Terminal-Bench · total_cost_usd727.02USD

z-ai/glm-5.3-flash

MetricValueUnit
Terminal-Bench · accuracy0.3697percent
Terminal-Bench · avg_trial_duration_sec120.4seconds
Terminal-Bench · pass_at_20.4833percent
Terminal-Bench · pass_at_30.5424percent
Terminal-Bench · pass_at_40.5879percent
Terminal-Bench · pass_at_50.6212percent
Terminal-Bench · total_cost_usd374.72USD

openai/gpt-5.4-mini

MetricValueUnit
Terminal-Bench · accuracy0.0182percent
Terminal-Bench · avg_trial_duration_sec141.5seconds
Terminal-Bench · pass_at_20.0318percent
Terminal-Bench · pass_at_30.0424percent
Terminal-Bench · pass_at_40.0515percent
Terminal-Bench · pass_at_50.0606percent
Terminal-Bench · total_cost_usd671.57USD

openai/gpt-6.1-terra

MetricValueUnit
Terminal-Bench · accuracy0.5333percent
Terminal-Bench · avg_trial_duration_sec123.1seconds
Terminal-Bench · pass_at_20.6152percent
Terminal-Bench · pass_at_30.6485percent
Terminal-Bench · pass_at_40.6636percent
Terminal-Bench · pass_at_50.6667percent
Terminal-Bench · total_cost_usd874.44USD

anthropic/claude-haiku-5-5

MetricValueUnit
Terminal-Bench · accuracy0.4percent
Terminal-Bench · avg_trial_duration_sec140.5seconds
Terminal-Bench · pass_at_20.5121percent
Terminal-Bench · pass_at_30.5636percent
Terminal-Bench · pass_at_40.5909percent
Terminal-Bench · pass_at_50.6061percent
Terminal-Bench · total_cost_usd952.47USD

openrouter/tencent/hy4

MetricValueUnit
Terminal-Bench · accuracy0.3788percent
Terminal-Bench · avg_trial_duration_sec126.2seconds
Terminal-Bench · pass_at_20.4848percent
Terminal-Bench · pass_at_30.5394percent
Terminal-Bench · pass_at_40.5727percent
Terminal-Bench · pass_at_50.5909percent
Terminal-Bench · total_cost_usd347.6USD

openrouter/thinkingmachines/inkling

MetricValueUnit
Terminal-Bench · accuracy0percent
Terminal-Bench · avg_trial_duration_sec174.1seconds
Terminal-Bench · pass_at_20percent
Terminal-Bench · pass_at_30percent
Terminal-Bench · pass_at_40percent
Terminal-Bench · pass_at_50percent
Terminal-Bench · total_cost_usd1011.52USD

openrouter/thinkingmachines/inkling-small

MetricValueUnit
Terminal-Bench · accuracy0.0091percent
Terminal-Bench · avg_trial_duration_sec141.3seconds
Terminal-Bench · pass_at_20.0167percent
Terminal-Bench · pass_at_30.0227percent
Terminal-Bench · pass_at_40.0273percent
Terminal-Bench · pass_at_50.0303percent
Terminal-Bench · total_cost_usd49.55USD

moonshotai/kimi-k3.1-pro

MetricValueUnit
Terminal-Bench · accuracy0.597percent
Terminal-Bench · avg_trial_duration_sec123.2seconds
Terminal-Bench · pass_at_20.747percent
Terminal-Bench · pass_at_30.8076percent
Terminal-Bench · pass_at_40.8364percent
Terminal-Bench · pass_at_50.8485percent
Terminal-Bench · total_cost_usd1086.66USD

openrouter/moonshotai/kimi-k3

MetricValueUnit
Terminal-Bench · accuracy0.2303percent
Terminal-Bench · avg_trial_duration_sec141.9seconds
Terminal-Bench · pass_at_20.35percent
Terminal-Bench · pass_at_30.4273percent
Terminal-Bench · pass_at_40.4848percent
Terminal-Bench · pass_at_50.5303percent
Terminal-Bench · total_cost_usd1919.83USD

openrouter/xiaomi/mimo-v2.6-flash

MetricValueUnit
Terminal-Bench · accuracy0.1606percent
Terminal-Bench · avg_trial_duration_sec160.8seconds
Terminal-Bench · pass_at_20.2576percent
Terminal-Bench · pass_at_30.3182percent
Terminal-Bench · pass_at_40.3576percent
Terminal-Bench · pass_at_50.3788percent
Terminal-Bench · total_cost_usd194.6USD

openrouter/xiaomi/mimo-v2.6-pro

MetricValueUnit
Terminal-Bench · accuracy0.2697percent
Terminal-Bench · avg_trial_duration_sec168.2seconds
Terminal-Bench · pass_at_20.3818percent
Terminal-Bench · pass_at_30.447percent
Terminal-Bench · pass_at_40.4939percent
Terminal-Bench · pass_at_50.5303percent
Terminal-Bench · total_cost_usd282.32USD

openrouter/minimax/minimax-m3

MetricValueUnit
Terminal-Bench · accuracy0.0758percent
Terminal-Bench · avg_trial_duration_sec204seconds
Terminal-Bench · pass_at_20.1409percent
Terminal-Bench · pass_at_30.1955percent
Terminal-Bench · pass_at_40.2394percent
Terminal-Bench · pass_at_50.2727percent
Terminal-Bench · total_cost_usd1149.33USD

openrouter/mistralai/mistral-large-4-0

MetricValueUnit
Terminal-Bench · accuracy0.2758percent
Terminal-Bench · avg_trial_duration_sec142.7seconds
Terminal-Bench · pass_at_20.4045percent
Terminal-Bench · pass_at_30.4848percent
Terminal-Bench · pass_at_40.5394percent
Terminal-Bench · pass_at_50.5758percent
Terminal-Bench · total_cost_usd718.4USD

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace