Vals-hosted Terminal-Bench 2.0 mirror (Vals Terminal-Bench 2.0 mirror)

We show this table for reference; we do not rank on it.

Data verified June 4, 202634 confirmed releases in the last 30 daysFollow model changes

Vals AI hosted Terminal-Bench 2.0 view with easy, medium, and hard task splits.

Vals Terminal-Bench 2.0 mirror score on Vals Terminal-Bench 2.0 mirror — June 4, 2026

We mirror the published vals terminal-bench 2.0 mirror score view for Vals Terminal-Bench 2.0 mirror. GPT-5.5 leads the public snapshot at 73.20%, followed by Claude Opus 4.8 (70.04%) and Claude Opus 4.7 (68.54%). We do not use these results to rank models overall.

1Proprietary

GPT-5.5

OpenAI

high reasoning

73.20%

Overall 69.13Context 1M

2Proprietary

Claude Opus 4.8

Anthropic

70.04%

Overall 70.46Context 1M

3Proprietary

Claude Opus 4.7

Anthropic

68.54%

Overall 66.28Context 1M

67 modelsAgenticCurrentDisplay onlyUpdated June 4, 2026

Vals Terminal-Bench 2.0 mirror score table (67 models)

Score

GPT-5.5OpenAI · Closedhigh reasoning

73.20%

Claude Opus 4.8Anthropic · Closed

70.04%

Claude Opus 4.7Anthropic · Closed

68.54%

Gemini 3.5 FlashGoogle · Closedhigh reasoning

67.42%

Gemini 3.1 Pro PreviewGooglehigh reasoning

67.42%

GPT-5.3 CodexOpenAI · Closedhigh reasoning

64.05%

Muse SparkMeta · Closed

59.55%

Claude Sonnet 4.6Anthropic · Closed

59.55%

Qwen3.7 MaxAlibaba · Closed

59.18%

Claude Opus 4.5Anthropic · Closed

58.43%

Claude Opus 4.6 (Adaptive)Anthropic · Closed

58.43%

GPT-5.4OpenAI · Closedhigh reasoning

58.43%

Kimi K2.6Moonshot AI · Open weight

57.30%

DeepSeek V4 Pro 0813DeepSeek · Open weight

56.18%

Gemini 3 Pro PreviewGooglehigh reasoning

55.06%

Claude Opus 4.5 ThinkingAnthropic · Closed

53.93%

GLM-5.1Z.AI · Open weight

53.93%

Gemini 3 Flash PreviewGooglehigh reasoning

51.69%

GPT-5.2OpenAI · Closedhigh reasoning

51.69%

Qwen 3.6 Max (preview)Alibaba · Closed

51.69%

GLM 5 ThinkingZhipu AI

49.44%

MiniMax M2.7MiniMax · Open weight

47.19%

MiniMax M3MiniMax · Open weight

46.07%

Qwen3.6 PlusAlibaba · Closed

44.94%

GPT-5.1OpenAI · Closedhigh reasoning

44.94%

Qwen3.6-27BAlibaba · Open weight

44.94%

GPT-5.4 miniOpenAI · Closedhigh reasoning

44.94%

Grok 4.3xAI · Closed

43.45%

Claude Sonnet 4.5 ThinkingAnthropic · Closed

41.57%

MiniMax M2.5MiniMax · Closed

41.57%

Qwen3.5 Plus ThinkingAlibaba

41.57%

Grok 4.20 0309 ReasoningxAI

40.45%

Kimi K2.5 ThinkingMoonshot AI

40.45%

GPT-5.4 nanoOpenAI · Closedhigh reasoning

39.89%

Gemma 4 31b ItGooglehigh reasoning

39.33%

Claude Haiku 4.5 ThinkingAnthropic · Closed

38.20%

GLM-4.7Z.AI · Open weight

38.20%

MiniMax M2.1MiniMax

37.08%

GPT-5OpenAIhigh reasoning

37.08%

Kimi K2 ThinkingMoonshot AI

37.08%

DeepSeek V3p2 ThinkingFireworks AIhigh reasoning

35.95%

DeepSeek V3p2Fireworks AInone reasoning

34.83%

Laguna M.1Poolside · Closed

31.46%

Gemini 2.5 ProGoogle · Closed

30.34%

Mistral Medium 3.5Mistral AIhigh reasoning

30.34%

Grok 4 Fast (Reasoning)xAI · Closed

29.21%

Laguna XS.2Poolside · Open weight

28.09%

GLM-4.6Z.AI · Open weight

28.09%

Grok 4 0709xAI

28.09%

GPT-5 miniOpenAI · Closedhigh reasoning

26.97%

Moonshotai Kimi K2 InstructTogether AI

25.84%

Grok 4.1 Fast (Reasoning)xAI · Closed

24.72%

Gemini 3.1 Flash Lite PreviewGooglehigh reasoning

24.72%

Qwen3.5 FlashAlibaba · Closed

24.72%

Qwen3 MaxAlibaba · Closed

24.72%

DeepSeek V3p1Fireworks AI

22.47%

Gemini 2.5 Flash Preview 09 2025 ThinkingGoogle

21.35%

Qwen3 MaxAlibaba · Closed

20.23%

GPT-OSS 120BOpenAI · Open weight

19.10%

Grok 4.1 Fast Non ReasoningxAI

17.98%

Trinity-Large-ThinkingArcee AI · Open weight

17.98%

Mistral Small 2603Mistral AIhigh reasoning

16.85%

GPT-4.1OpenAI · Closedhigh reasoning

14.61%

Magistral Medium 2509Mistral AI

13.48%

Mistral Large 2512Mistral AI

8.99%

Command A 03 2025Cohere

2.25%

Llama4 Maverick Instruct BasicFireworks AI

2.25%

How Vals Terminal-Bench 2.0 mirror is shown here

BenchLM mirrors the public Vals AI Vals Terminal-Bench 2.0 mirror leaderboard captured from https://www.vals.ai/benchmarks/terminal-bench-2 and updated by Vals on June 4, 2026. The snapshot preserves overall scores, uncertainty, latency, cost-per-test metadata, and task-level scores where Vals publishes them.

Vals Terminal-Bench 2.0 mirror is display only on BenchLM. Vals proprietary or Vals-hosted aggregate views are useful context, but BenchLM does not use them as weighted ranking inputs or as a replacement for benchmark-native source records.

Snapshot

67 Vals rows4 task viewspublic datasetTasks: Overall, Easy, Medium, HardDisplay only

Vals Terminal-Bench 2.0 mirror on Vals AI Vals methodology Vals home

The published Vals Terminal-Bench 2.0 mirror snapshot places GPT-5.5 first at 73.20%. The third row is 4.66 points behind. The broader top-10 range is 14.77 points, so the table still separates the published systems.

67 models have been evaluated on Vals Terminal-Bench 2.0 mirror. The benchmark falls in the Agentic category. We keep external benchmark mirrors separate from the weighted global scoring system, so these results remain source-specific evidence. Vals Terminal-Bench 2.0 mirror is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About Vals Terminal-Bench 2.0 mirror

Year

2026

Tasks

Terminal task difficulty splits

Format

Accuracy score

Difficulty

Terminal-based agent execution

BenchLM mirrors this Vals-hosted Terminal-Bench view as display-only secondary context.

Vals Terminal-Bench 2.0 Public benchmark source

Freshness and provenance

Version

Vals Terminal-Bench 2.0 mirror 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Questions

What does Vals Terminal-Bench 2.0 mirror measure?

Vals AI hosted Terminal-Bench 2.0 view with easy, medium, and hard task splits.

Which model leads the published Vals Terminal-Bench 2.0 mirror snapshot?

GPT-5.5 currently leads the published Vals Terminal-Bench 2.0 mirror snapshot with 73.20% vals terminal-bench 2.0 mirror score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on Vals Terminal-Bench 2.0 mirror?

The June 4, 2026 snapshot contains 67 AI models.

Last updated: June 4, 2026 · mirrored from the public benchmark leaderboard

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.