Skip to main content
Radar

Keep up with the models you depend on. Follow price changes, retirements, and API updates.Follow the models you depend on.

Follow model changes

Artificial Analysis Terminal-Bench v4.0 (AA Terminal-Bench 4.0)

An independently evaluated Terminal-Bench v4.0 result from Artificial Analysis, one of the ten components of its Intelligence Index v4.3.

Data verified 37 confirmed releases in the last 30 daysSee provider release alerts

Benchmark score on AA Terminal-Bench 4.0 — September 10, 2026

We mirror the published score view for AA Terminal-Bench 4.0. GPT-6 Astra leads the public snapshot at 59.1%, followed by Claude Fable 5.1 (52.0%) and Claude Opus 5 (49.0%). We do not use these results to rank models overall.

15 modelsAgenticCurrentDisplay onlyUpdated September 10, 2026

Benchmark score table (15 models)

Score
1
GPT-6 AstraOpenAI · Closed
59.1%
2
Claude Fable 5.1Anthropic · Closed
52.0%
3
Claude Opus 5Anthropic · Closed
49.0%
4
Claude Fable 5Anthropic · Closed
42.4%
5
GLM-5.3Z.AI · Open weight
41.9%
6
GPT-5.6 SolOpenAI · Closed
39.9%
7
GPT-5.6 TerraOpenAI · Closed
35.4%
8
Muse Spark 1.3Meta · Closed
33.3%
9
GLM-5.3-FlashZ.AI · Open weight
32.8%
10
DeepSeek V4.1 FlashDeepSeek · Open weight
26.8%
11
Grok 4.6xAI · Closed
21.2%
12
Gemini 3.8 FlashGoogle · Closed
19.7%
13
DeepSeek V4 Pro 0813DeepSeek · Closed
14.1%
14
Kimi K3Moonshot AI · Closed
12.6%
15
GPT-5.6 LunaOpenAI · Closed
11.6%

The published AA Terminal-Bench 4.0 snapshot places GPT-6 Astra first at 59.1%. The third row is 10.1 points behind. The broader top-10 range is 32.3 points, so the table still separates the published systems.

15 models have been evaluated on AA Terminal-Bench 4.0. The benchmark falls in the Agentic category. This category carries a 22% weight in BenchLM.ai's overall scoring system. AA Terminal-Bench 4.0 is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About AA Terminal-Bench 4.0

Year

2026

Tasks

Terminal-based agent tasks

Format

Task success rate

Difficulty

Agentic software engineering

Stored separately from the benchmark-owned Terminal-Bench 4.0 lane because Artificial Analysis controls the agent harness and configuration. Display-only; not yet admitted as independent-run evidence.

BenchLM freshness & provenance

Version

AA Terminal-Bench 4.0 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.

FAQ

What does AA Terminal-Bench 4.0 measure?

An independently evaluated Terminal-Bench v4.0 result from Artificial Analysis, one of the ten components of its Intelligence Index v4.3.

Which model scores highest on AA Terminal-Bench 4.0?

GPT-6 Astra by OpenAI currently leads with a score of 59.1% on AA Terminal-Bench 4.0.

How many models are evaluated on AA Terminal-Bench 4.0?

15 AI models have been evaluated on AA Terminal-Bench 4.0 on BenchLM.

Last updated: September 10, 2026 · BenchLM version AA Terminal-Bench 4.0 2026

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.