Vibeleaderboard
← Benchmark guide

Model results

Terminal-Bench

Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.

Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.

Reviewed recommendation and limits

Start with Terminal-Bench 4.0 for terminal-based agent work. Compare the same task release, agent and resource settings.

Terminal-Bench 4.0.0 on Harbor. Preserve agent, model, reasoning effort, task resources, trial count and resolution-rate uncertainty. Earlier 2.0, 2.1 and 3.0 results remain separate.. Imported groups below may use different protocols; this review does not certify each run. Public solutions, reward hacking and task-specific tuning can inflate results. Earlier editions and vendor-reported runs do not establish the current reviewed protocol. Terminal completion is different from repository issue repair.

Publisher results Terminal-Bench 4.0 Leaderboard integrity policy Contributors

Evaluation groups

Open a group to see its exact protocol and scores. Different configurations remain separate.

Model rankings

Open a group to compare scores within its reported protocol. Positions do not establish statistical significance.

Other reported results

These reports have no model ranking. Open a group for its evidence and the reason positions are withheld.

  • Claude Opus 5.54.0

    Terminal-Bench 4.0 · Anthropic (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date 2026-09-22

    Scope · Vendor-reported in Anthropic's Claude Opus 5.5 launch table; adaptive thinking at max effort unless …

    Vendor-reported in Anthropic's Claude Opus 5.5 launch table; adaptive thinking at max effort unless noted; evaluated with production safeguards on, and where they intervened, cybersecurity tasks fell back to Claude Opus 4.8 and biology/frontier-LLM tasks to Claude Opus 5 (Anthropic says this likely lowers scores); xhigh effort (its highest score); standard error ±2.6 pts; Anthropic's setup reproduces the public leaderboard's Opus 5 result within noise (52.3% vs 51.8%, 5 trials/task, Claude Code harness); dated to the announcement

  • DeepSeek V4.1 Flash4.0

    Terminal-Bench 4.0 · DeepSeek model card (vendor-reported)

    Single-model result · Positions withheld

    Measurement date 2026-09-10

    Scope · Vendor-reported; reasoning effort 100; Pass@1; temperature 1.0, top_p 0.95; DeepSeek Harness Minimal…

    Vendor-reported; reasoning effort 100; Pass@1; temperature 1.0, top_p 0.95; DeepSeek Harness Minimal; 1M context

  • DeepSeek V4.1 Flash3.0

    Terminal-Bench 3.0 · DeepSeek model card (vendor-reported)

    Single-model result · Positions withheld

    Measurement date 2026-09-10

    Scope · Vendor-reported; reasoning effort 100; Pass@1; temperature 1.0, top_p 0.95; DeepSeek Harness Minimal…

    Vendor-reported; reasoning effort 100; Pass@1; temperature 1.0, top_p 0.95; DeepSeek Harness Minimal; 1M context

  • Muse Spark Open2.1

    terminal-bench-2.1 · terminalbench 2 1 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-10-15

    Scope · Registered model evaluation · Muse Spark Open model card

  • Beam 1.0 501B A23B2.1

    terminal-bench-2.1 · terminalbench 2 1 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-10-07

    Scope · Registered model evaluation · dataset harborframework/terminal-bench-2.1 · task terminalbench_2_1 · …

    Registered model evaluation · dataset harborframework/terminal-bench-2.1 · task terminalbench_2_1 · Beam 1.0 model card

  • MiMo-V2.6-Flash2.1

    terminal-bench-2.1 · terminalbench 2 1 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-09-22

    Scope · Registered model evaluation · MiMo-V2.6-Flash-RL model card

  • MiMo-V2.6-Pro2.1

    terminal-bench-2.1 · terminalbench 2 1 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-09-22

    Scope · Registered model evaluation · MiMo-V2.6-Pro-RL model card

  • Nex-N2.5-Pro2.1

    terminal-bench-2.1 · terminalbench 2 1 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-09-11

    Scope · Registered model evaluation · Nex-N2.5 model card

  • DeepSeek V4.1 Flash2.1

    Terminal-Bench 2.1 · DeepSeek model card (vendor-reported)

    Single-model result · Positions withheld

    Measurement date 2026-09-10

    Scope · Vendor-reported; reasoning effort 100; Pass@1; temperature 1.0, top_p 0.95; DeepSeek Harness Minimal…

    Vendor-reported; reasoning effort 100; Pass@1; temperature 1.0, top_p 0.95; DeepSeek Harness Minimal; 1M context

  • DeepSeek V4.1 Flash2.1

    terminal-bench-2.1 · terminalbench 2 1 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-09-10

    Scope · Registered model evaluation · DeepSeek-V4.1-Flash model card

  • terminal-bench-2.1 · terminalbench 2 12.1

    Hugging Face eval result

    5 models with scores · Positions withheld

    Measurement date 2026-08-31

    Scope · Registered model evaluation · Model Card

  • GLM 5.3 Flash2.1

    terminal-bench-2.1 · terminalbench 2 1 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-08-26

    Scope · Registered model evaluation · GLM-5.3-Flash model card

  • Laguna S 2.12.1

    terminal-bench-2.1 · terminalbench 2 1 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-08-26

    Scope · Registered model evaluation · Model Card

  • Qwen3.8 27B2.1

    terminal-bench-2.1 · terminalbench 2 1 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-08-14

    Scope · Registered model evaluation · Model Card

  • terminal-bench-2.1 · terminalbench 2 12.1

    Hugging Face eval result

    2 models with scores · Positions withheld

    Measurement date 2026-08-13

    Scope · Registered model evaluation · Model Card

  • Qwen3.8 2.4T A95B2.1

    terminal-bench-2.1 · terminalbench 2 1 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-08-12

    Scope · Registered model evaluation · Model Card

  • Muse Glimmer 30B2.1

    terminal-bench-2.1 · terminalbench 2 1 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-08-11

    Scope · Registered model evaluation · Model Card

  • DeepSeek V4 Flash 07312.1

    terminal-bench-2.1 · terminalbench 2 1 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-08-01

    Scope · Registered model evaluation · Model Card

  • Hy32.1

    terminal-bench-2.1 · terminalbench 2 1 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-07-20

    Scope · Registered model evaluation · Model Card

  • Inkling2.1

    terminal-bench-2.1 · terminalbench 2 1 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-07-15

    Scope · Registered model evaluation · Model Card

  • LongCat 2.02.1

    terminal-bench-2.1 · terminalbench 2 1 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-07-08

    Scope · Registered model evaluation · Model Card

  • GLM 5.22.1

    terminal-bench-2.1 · terminalbench 2 1 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-07-02

    Scope · Registered model evaluation · Model Card

  • Nemotron 3 Ultra2.1

    terminal-bench-2.1 · terminalbench 2 1 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-06-10

    Scope · Registered model evaluation · Model Card

  • Step 3.7 Flash2.1

    terminal-bench-2.1 · terminalbench 2 1 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-06-03

    Scope · Registered model evaluation · Model Card

  • Xing4.0-29B-A4B2.1

    Terminal-Bench 2.1 · XingChen-AGI model card

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Publisher model-card report; measurement date and metric unit unreported. terminus-2; temperature 0.…

    Publisher model-card report; measurement date and metric unit unreported. terminus-2; temperature 0.8, top_p 0.95, repetition_penalty 1.05, max_tokens 64K, 24-hour timeout. Average over three runs.

  • Laguna XS 2.12.0

    terminal-bench-2.0 · terminalbench 2 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-07-02

    Scope · Registered model evaluation · Model Card

  • Qwen3.6 27B2.0

    terminal-bench-2.0 · terminalbench 2 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-06-23

    Scope · Registered model evaluation · Model Card

  • North Mini Code2.0

    terminal-bench-2.0 · terminalbench 2 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-06-09

    Scope · Registered model evaluation · North Mini Code Model Page

  • terminal-bench-2.0 · terminalbench 22.0

    Hugging Face eval result

    2 models with scores · Positions withheld

    Measurement date 2026-04-27

    Scope · Registered model evaluation · Model Card

  • terminal-bench-2.0 · terminalbench 22.0

    Hugging Face eval result

    2 models with scores · Positions withheld

    Measurement date 2026-04-24

    Scope · Registered model evaluation · Model Card

  • Kimi K2.62.0

    terminal-bench-2.0 · terminalbench 2 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-04-20

    Scope · Registered model evaluation · Model Card

  • Qwen3.6 35B A3B2.0

    terminal-bench-2.0 · terminalbench 2 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-04-16

    Scope · Registered model evaluation · Model Card

  • Hy3 preview2.0

    terminal-bench-2.0 · terminalbench 2 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-04-14

    Scope · Registered model evaluation · Model Card

  • MiniMax M2.72.0

    terminal-bench-2.0 · terminalbench 2 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-04-12

    Scope · Registered model evaluation · Model Card

  • GLM 5.12.0

    terminal-bench-2.0 · terminalbench 2 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-04-07

    Scope · Registered model evaluation · Model Card

  • Qwen3 Coder Next2.0

    terminal-bench-2.0 · terminalbench 2 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-03-16

    Scope · Registered model evaluation · Model Card

  • terminal-bench-2.0 · terminalbench 22.0

    Hugging Face eval result

    3 models with scores · Positions withheld

    Measurement date 2026-02-25

    Scope · Registered model evaluation · Model Card

  • GLM 52.0

    terminal-bench-2.0 · terminal bench · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-02-23

    Scope · Registered model evaluation · Terminal-Bench Leaderboard

  • Step 3.5 Flash2.0

    terminal-bench-2.0 · terminalbench 2 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-02-11

    Scope · Registered model evaluation · Step 3.5 Flash Paper

  • DeepSeek V3.22.0

    terminal-bench-2.0 · terminalbench 2 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-02-10

    Scope · Registered model evaluation · Terminal-Bench Leaderboard

  • Kimi K2.52.0

    terminal-bench-2.0 · terminalbench 2 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-02-04

    Scope · Registered model evaluation · Terminal-Bench Leaderboard

  • Qwen3.5 397B A17B2.0

    terminal-bench-2.0 · terminalbench 2 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-02-03

    Scope · Registered model evaluation · Model Card

  • GLM 4.72.0

    terminal-bench-2.0 · terminalbench 2 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-01-28

    Scope · Registered model evaluation · Terminal-Bench Leaderboard

  • MiniMax M2.12.0

    terminal-bench-2.0 · terminalbench 2 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2025-12-23

    Scope · Registered model evaluation · Terminal-Bench Leaderboard

  • Kimi K2 Thinking2.0

    terminal-bench-2.0 · terminalbench 2 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2025-11-11

    Scope · Registered model evaluation · Terminal-Bench Leaderboard

  • terminal-bench-2.0 · terminalbench 22.0

    Hugging Face eval result

    4 models with scores · Positions withheld

    Measurement date 2025-11-01

    Scope · Registered model evaluation · Terminal-Bench Leaderboard

  • Claude Opus 4.52.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent Letta Code · effort 128K · result date not supplied

  • Claude Opus 4.52.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent Letta Code · effort unspecified · result date not supplied

  • Claude Opus 4.52.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent OpenCode · effort unspecified · result date not supplied

  • Claude Opus 4.62.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent Crux · effort unspecified · result date not supplied

  • Claude Opus 4.62.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent Meta-Harness · effort unspecified · result date not supplied

  • Claude Opus 4.62.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent Terminus-KIRA · effort unspecified · result date not supplied

  • Claude Opus 4.62.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent TongAgents · effort unspecified · result date not supplied

  • Claude Opus 4.72.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent WOZCODE · effort unspecified · result date not supplied

  • Claude Sonnet 4.52.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent CAMEL-AI · effort unspecified · result date not supplied

  • Claude Sonnet 4.52.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent MAYA · effort unspecified · result date not supplied

  • Claude Sonnet 4.62.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent Simplai Agent · effort unspecified · result date not supplied

  • Claude Sonnet 4.62.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent Simplai Agent · result date not supplied

  • Gemini 3 Flash Preview2.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent Junie CLI · result date not supplied

  • Gemini 3.1 Pro Preview2.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent Forge Code · result date not supplied

  • Gemini 3.1 Pro Preview2.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent ForgeCode · result date not supplied

  • Gemini 3.1 Pro Preview2.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent Terminus-KIRA · result date not supplied

  • Gemini 3.1 Pro Preview2.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent TongAgents · result date not supplied

  • GPT-5 Mini2.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent spoox-m · effort unspecified · result date not supplied

  • GPT-5.1-Codex2.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent Letta Code · result date not supplied

  • GPT-5.1-Codex-Mini2.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent hookele · result date not supplied

  • GPT-5.22.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent Droid · effort medium · result date not supplied

  • GPT-5.2-Codex2.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent Deep Agents · result date not supplied

  • GPT-5.3-Codex2.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent CodeBrain-1 · result date not supplied

  • GPT-5.3-Codex2.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent CodeBrain-1.5 · result date not supplied

  • GPT-5.3-Codex2.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent Codelia · result date not supplied

  • GPT-5.3-Codex2.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent Mux · result date not supplied

  • GPT-5.3-Codex2.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent SageAgent · result date not supplied

  • GPT-5.3-Codex2.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent Simple Codex · result date not supplied

  • GPT-5.3-Codex2.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent spoox-o-m · result date not supplied

  • GPT-5.52.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent clnkr · effort unspecified · result date not supplied

  • GPT-5.52.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent Codex · effort unspecified · result date not supplied

  • GPT-5.52.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent NexAU-AHE · effort unspecified · result date not supplied

  • Grok 4.202.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent Grok CLI · result date not supplied

  • Grok 4.202.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent grok-cli · result date not supplied

  • MiniMax M2.52.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent cchuter · result date not supplied

  • MiniMax M2.72.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent Harness Agent · result date not supplied

  • Qwen3 Coder 480B A35B2.0

    Terminal-Bench 2.0 · Terminal-Bench via Epoch AI

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Agent Dakou Agent · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    2 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent Capy · effort unspecified · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    5 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent Claude Code · effort unspecified · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    3 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent Claude Code · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    4 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent Codex CLI · effort medium · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    5 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent Codex CLI · effort unspecified · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    4 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent Codex CLI · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    4 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent Crux · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    3 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent Droid · effort unspecified · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    3 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent Droid · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    2 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent ForgeCode · effort unspecified · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    3 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent Gemini CLI · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    3 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent Goose · effort unspecified · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    2 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent IndusAGI Coding Agent · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    2 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent little-coder · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    2 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent MAYA-V2 · effort unspecified · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    3 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent Mini-SWE-Agent · effort medium · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    8 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent Mini-SWE-Agent · effort unspecified · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    8 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent Mini-SWE-Agent · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    3 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent Mux · effort unspecified · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    3 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent OpenHands · effort medium · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    7 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent OpenHands · effort unspecified · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    7 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent OpenHands · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    2 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent spoox-o-m · effort unspecified · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    4 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent Terminus 2 · effort medium · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    12 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent Terminus 2 · effort unspecified · result date not supplied

  • Terminal-Bench 2.02.0

    Terminal-Bench via Epoch AI

    21 models with scores · Positions withheld

    Measurement date not reported

    Scope · Agent Terminus 2 · result date not supplied

  • MiMo-V2.5-ProVersion not reported

    terminal-bench · terminalbench 4 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-09-22

    Scope · Registered model evaluation · MiMo-V2.6 Technical Report (Table 3, MiMo-V2.5 Pro baseline column)

  • MiMo-V2.6-FlashVersion not reported

    terminal-bench · terminalbench 4 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-09-22

    Scope · Registered model evaluation · MiMo-V2.6-Flash-RL model card

  • MiMo-V2.6-ProVersion not reported

    terminal-bench · terminalbench 4 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-09-22

    Scope · Registered model evaluation · MiMo-V2.6-Pro-RL model card

  • Step 5 PreviewVersion not reported

    terminal-bench · terminalbench 4 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-09-20

    Scope · Registered model evaluation · Step 5 Preview model card

  • DeepSeek V4.1 FlashVersion not reported

    terminal-bench · terminalbench 3 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-09-10

    Scope · Registered model evaluation · DeepSeek-V4.1-Flash model card

  • DeepSeek V4.1 FlashVersion not reported

    terminal-bench · terminalbench 4 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-09-10

    Scope · Registered model evaluation · DeepSeek-V4.1-Flash model card

  • GLM 5.3Version not reported

    terminal-bench · terminalbench 3 · Hugging Face eval result

    Single-model result · Positions withheld

    Measurement date 2026-09-04

    Scope · Registered model evaluation · Model Card

  • Terminal-BenchVersion not reported

    Hugging Face OpenEvals

    16 models with scores · Positions withheld

    Measurement date not reported

    Scope · Latest published official benchmark result aggregated by OpenEvals · result date not supplied

Terminal-Bench model results | VibeLeaderboard