Work Automations
Private 657 tasks; 50 turns; objective completion
- 01
- 02
- 03
- 04
- 05
- 29
GPT-5.6 Luna
Across the task benchmarks we track, GPT-5.6 Luna’s strongest relative results are in work automations. On AutomationBench-AA, it scores 50.2%, ranking #29 among 55 models with reported results in our dataset.
Updated: Data as of:
Strongest results
| Benchmark | Measures | Score |
|---|---|---|
| GDP.pdf ↗100 tasks / All-pass / five attempts | Professional document reasoning | 24%#13 of 55 |
| AA-Briefcase ↗1.1 / combined Elo | Business deliverables | 1,339 Elo#26 of 57 |
| Humanity's Last Exam ↗Stable HLE — text-only subset | Expert reasoning | 39.5%#35 of 68 |
| AutomationBench-AA ↗1.0.6 / AA private 657 | Work automations | 50.2%#29 of 55 |
Model details
| Model | GPT-5.6 Luna |
|---|---|
| Agent Index v1.2 | Insufficient coverage (3/7) · Preview |
| Creator | OpenAI (opens in a new tab) |
| Availability | Proprietary |
| Context size | Not reported |
| Max output | Not reported |
| Knowledge cutoff | Not reported |
| License | Not reported |
Pricing and performance
Per provider and reported configuration. Prices are USD per 1M tokens.
No provider pricing or performance reports have been added for this model yet.
Benchmark performance
GPT-5.6 Luna in color, alongside leading models. Latest stored reports, best effort per report date.
AutomationBench-AA ↗
Reported benchmarks
All published results in our dataset, with versions, evaluation settings, and sources.
| Benchmark | Score | Evaluation setup | Source |
|---|---|---|---|
| AA-Briefcase1.1 / combined EloCombined Elo · Higher is better | 1,339 Elo | selection: best reported configuration per release · GPT-5.6 Luna (max) · tools: benchmark-defined | Artificial Analysis (opens in a new tab)independent |
| AppWorldTest-ChallengeTask Goal Completion · Higher is better | 73.4% | agent: kecaipan capybara · metric: TGC · selection: All 23 leaderboard submissions; latest report date and best score at that date shown per model. Normal-split and SGC values retained in the source data/settings, not mixed into the ranking. · source model label: gpt-5.6-luna · split: Test-Challenge · test challenge sgc: 52.5 · test normal sgc: 73.2 · test normal tgc: 85.1 | AppWorld research team ↗ (opens in a new tab)benchmark publisher · 2026-08-08 |
| AutomationBench-AA1.0.6 / AA private 657Objectives completed without guardrail violations · Higher is better | 50.2% | reported precision decimals: 1 · result quality: reported · GPT-5.6 Luna (max); private held-out 657 tasks; 50 turns; objective completion with zero credit for any guardrail violation. · source model href: /models/gpt-5-6-luna · task count: 657 · Tools enabled · turn cap: 50 | Artificial Analysis (opens in a new tab)independent |
| GDP.pdf100 tasks / All-pass / five attemptsAccuracy · Higher is better | 24% | selection: best reported configuration per release · GPT-5.6 Luna (max) · tools: benchmark-defined | Artificial Analysis (opens in a new tab)independent |
| Humanity's Last ExamStable HLE — text-only subsetAccuracy · Higher is better | 39.5% | question count: 2158 · reported precision decimals: 1 · GPT-5.6 Luna (max); original HLE; 2,158 text-only questions; no tools; pass@1; chart labels rounded to one decimal. · source model href: /models/gpt-5-6-luna · subset: text · No tools | Artificial Analysis (opens in a new tab)independent |
| MyPCBench184 tasks · 100 stepsPerfect-task rate · Higher is better | 55.4% | interface: computer + bash · judge: gemini-3.1-flash-lite-preview · max steps: 100 · rubric score percent: 83.2 · selection: Canonical matched-protocol rows only; four 200-step self-reported rows retained in source snapshot, excluded from this track. · tasks: 184 | MyPCBench / Carnegie Mellon University ↗ (opens in a new tab)benchmark publisher |
| Terminal-Bench4.0 / mini-swe-agentTask success · Higher is better | 11.6% | harness: mini-swe-agent · repeats: 3 · selection: best reported configuration per release · GPT-5.6 Luna (max) | Artificial Analysis (opens in a new tab)independent |