Work Automations
Private 657 tasks; 50 turns; objective completion
- 01
- 02
- 03
- 04
- 05
- 53
Qwen3-14B
Across the task benchmarks we track, Qwen3-14B’s strongest relative results are in work automations. On AutomationBench-AA, it scores 0.2%, ranking #53 among 55 models with reported results in our dataset.
Updated: Data as of:
Strongest results
| Benchmark | Measures | Score |
|---|---|---|
| Terminal-Bench ↗4.0 / mini-swe-agent | Working in a terminal | 0%Joint #49 of 56 |
| AutomationBench-AA ↗1.0.6 / AA private 657 | Work automations | 0.2%#53 of 55 |
| AA-Briefcase ↗1.1 / combined Elo | Business deliverables | 0 EloJoint #55 of 57 |
| Humanity's Last Exam ↗Stable HLE — text-only subset | Expert reasoning | 4.5%#66 of 68 |
Model details
| Model | Qwen3-14B |
|---|---|
| Agent Index v1.2 | Insufficient coverage (3/7) · Preview |
| Creator | Qwen (opens in a new tab) |
| Availability | Open source / open weights |
| Context size | Not reported |
| Max output | Not reported |
| Knowledge cutoff | Not reported |
| License | Not reported · Model weights ↗ (opens in a new tab) |
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
Qwen3-14B 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 | 0 Elo | selection: best reported configuration per release · Qwen3 14B · tools: benchmark-defined | Artificial Analysis (opens in a new tab)independent |
| AppWorldTest-ChallengeTask Goal Completion · Higher is better | 67.6% | agent: Alibaba Cloud ApsaraLab AgentRL · 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: Qwen3-14B · split: Test-Challenge · test challenge sgc: 50.4 · test normal sgc: 80.4 · test normal tgc: 86.9 | AppWorld research team ↗ (opens in a new tab)benchmark publisher · 2026-02-15 |
| AutomationBench-AA1.0.6 / AA private 657Objectives completed without guardrail violations · Higher is better | 0.2% | reported precision decimals: 1 · result quality: reported · Qwen3 14B; private held-out 657 tasks; 50 turns; objective completion with zero credit for any guardrail violation. · source model href: /models/qwen3-14b-instruct-reasoning · 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 | 1.2% | selection: best reported configuration per release · Qwen3 14B · tools: benchmark-defined | Artificial Analysis (opens in a new tab)independent |
| Humanity's Last ExamStable HLE — text-only subsetAccuracy · Higher is better | 4.5% | question count: 2158 · reported precision decimals: 1 · Qwen3 14B; original HLE; 2,158 text-only questions; no tools; pass@1; chart labels rounded to one decimal. · source model href: /models/qwen3-14b-instruct-reasoning · subset: text · No tools | Artificial Analysis (opens in a new tab)independent |
| Terminal-Bench4.0 / mini-swe-agentTask success · Higher is better | 0% | harness: mini-swe-agent · repeats: 3 · selection: best reported configuration per release · Qwen3 14B | Artificial Analysis (opens in a new tab)independent |