AI Model Capability Comparison
Agentic coding
Only models released within the past year are shown. Only benchmarks covering at least 3 of these models are shown. Unknown release dates are excluded; historical data is retained.
Vibe Code BenchVibe coding benchmark
— means no published score for this candidate in this source, not zero.10/11 recent-year models have scores
| No. | Model | Cost / TestCost per test | Input costInput price per million tokens | Output costOutput price per million tokens | DurationReported test duration | |
|---|---|---|---|---|---|---|
| 1 |  Claude Sonnet 5.5Claude Sonnet 5.5 | 92.39 | $31.25 | $2 | $10 | 61 min |
| 2 |  Gemini 4 ArgonGemini 4 Argon | 91.91 | $8.11 | $4 | $20 | 37.47 min |
| 3 | Claude Haiku 5.5Claude Haiku 5.5 | 90.44 | $6.07 | $0.1 | $0.5 | 34.6 min |
| 4 | Claude Opus 5.5Claude Opus 5.5 | 90.29 | $57.92 | $4 | $20 | 96 min |
| 5 | Claude Fable 5.1Claude Fable 5.1 | 90.26 | $33.37 | $10 | $50 | 57.67 min |
| 6 |  GPT-6 AstraGPT-6 Astra | 89.59 | $38.51 | $10 | $50 | 39.07 min |
| 7 | GPT-6.1 SolGPT-6.1 Sol | 88.93 | $6.23 | $2 | $10 | 75 min |
| 8 | Claude Opus 5Claude Opus 5 | 88.4 | $33.88 | $5 | $25 | 88 min |
| 9 | GPT-6 SolGPT-6 Sol | 87.82 | $26.36 | $2 | $10 | 38.93 min |
| 10 | GPT-6 LunaGPT-6 Luna | 81.65 | $1.35 | $0.1 | $0.5 | 37 min |
PandaNpc Updated Oct 21, 2026, 06:01 UTC
Source: Epoch AI, CC BY 4.0 · Vals.ai · Artificial Analysis (artificialanalysis.ai)
Column guide
- No.
- Display order only. Sorting changes this number; it is not a published capability rank.
- Model
- The evaluated model name and its provider icon. A dash in a score column means no published score is available here, not a zero.
- Score
- Tests building web applications from natural-language requests, evaluating the resulting application rather than isolated code answers. Evaluation methodology ↗
- Cost / Test
- Cost per test · USD
- Input cost
- Input price per million tokens · USD / 1M tokens
- Output cost
- Output price per million tokens · USD / 1M tokens
- Duration
- Reported test duration · s / min
- Vals.ai
- Costs and times are reported by Vals for this benchmark, not universal model prices or latency. CUA-bench estimated API cost covers evaluation usage and is a lower-bound estimate, not cost per task; time per action is an average, not a median. An asterisk marks launch-day prompt-cache behavior that increased cache-write costs. Missing values are unpublished, not zero.