Qwen3.8-Flash-Next
—No score is inferred or assigned a ranking position.
Agentic Ranking
AutomationBench-AA multi-step business workflows in the Artificial Analysis harness.
Method AutomationBench-AA multi-step business workflows in the Artificial Analysis harness.
Original scores from one independent snapshot. Each model keeps one evaluation configuration across the task lenses; rounded ties share a rank.
| Rank | Model | Provider | Agentic (%) | State | Coding (%) | Reasoning (%) | Research (Elo) | Multimodal (%) |
|---|---|---|---|---|---|---|---|---|
| 1 | 78% | Measured ↗ | 57% | 57% | 1611 | 22% | ||
| 2 | Anthropic | 71% | Measured ↗ | 64% | 55% | 1844 | 26% | |
| 3 | Anthropic | 70% | Measured ↗ | 60% | 61% | 1846 | 26% | |
| 4 | DeepSeek | 69% | Measured ↗ | 27% | 39% | 1600 | 13% | |
| 5 | OpenAI | 68% | Measured ↗ | 59% | 55% | 1542 | 31% | |
| 6 | xAI | 67% | Measured ↗ | 21% | 43% | 1609 | 17% | |
| 7 | xAI | 66% | Measured ↗ | 26% | 43% | 1695 | 20% | |
| 8 | OpenAI | 65% | Measured ↗ | 56% | 53% | 1575 | 31% | |
| 9 | Z.ai | 62% | Measured ↗ | 42% | 42% | 1656 | 11% | |
| 9 | OpenAI | 62% | Measured ↗ | 44% | 48% | 1505 | 25% | |
| 11 | 60% | Measured ↗ | 20% | 48% | 1412 | 21% | ||
| 11 | Z.ai | 60% | Measured ↗ | 33% | 40% | 1645 | 15% | |
| 13 | Anthropic | 59% | Measured ↗ | 52% | 59% | 1735 | 26% | |
| 14 | Moonshot AI | 58% | Measured ↗ | 13% | 47% | 1540 | 22% | |
| 15 | Alibaba Cloud | 56% | Measured ↗ | 39% | 43% | 1672 | 23% | |
| 16 | OpenAI | 53% | Measured ↗ | 13% | 39% | 1438 | 23% | |
| 17 | Alibaba Cloud | 49% | Measured ↗ | 19% | 43% | 1608 | 20% | |
| 18 | MiniMax | 21% | Measured ↗ | 2% | 39% | 1246 | 10% | |
| 19 | Mistral | 6% | Measured ↗ | 0% | 14% | 747 | 3% |
Other catalog models
No score for this exact benchmark in the selected snapshot. Available historical results remain in each profile.
Claude Sonnet 5
—No score is inferred or assigned a ranking position.
Claude Haiku 4.5
—No score is inferred or assigned a ranking position.
Claude Mythos 5.1
—No score is inferred or assigned a ranking position.
Gemini 3.8 Flash Cyber
—No score is inferred or assigned a ranking position.
GPT-5.6 Sol
—No score is inferred or assigned a ranking position.
GPT-5.6 Terra
—No score is inferred or assigned a ranking position.
GPT-5.6 Luna
—No score is inferred or assigned a ranking position.
Gemini 3.5 Flash
—No score is inferred or assigned a ranking position.
Gemini 3.6 Flash
—No score is inferred or assigned a ranking position.
Claude Fable 5
—No score is inferred or assigned a ranking position.
Claude Opus 5
—No score is inferred or assigned a ranking position.
Claude Opus 4.8
—No score is inferred or assigned a ranking position.
Claude Opus 4.7
—No score is inferred or assigned a ranking position.
DeepSeek V4 Pro
—No score is inferred or assigned a ranking position.
DeepSeek V4 Flash
—No score is inferred or assigned a ranking position.
OpenAI GPT-5.4
—No score is inferred or assigned a ranking position.
OpenAI GPT-5.2 Thinking
—No score is inferred or assigned a ranking position.
Claude Opus 4.6
—No score is inferred or assigned a ranking position.
Gemini 3.1 Pro
—No score is inferred or assigned a ranking position.
Gemini 3 Pro
—No score is inferred or assigned a ranking position.
DeepSeek-R1
—No score is inferred or assigned a ranking position.
Gemini 3.7 Flash
—No score is inferred or assigned a ranking position.
Qwen3.8-Flash
—No score is inferred or assigned a ranking position.
DeepSeek-V3
—No score is inferred or assigned a ranking position.
Tencent Hunyuan-Large
—No score is inferred or assigned a ranking position.
Hunyuan-T1
—No score is inferred or assigned a ranking position.
Artificial Analysis Intelligence Index v4.3.2
Original metrics and evaluation configurations remain authoritative. Checked 2026-10-02.
Artificial Analysis methodology
Original metrics and evaluation configurations remain authoritative. Checked 2026-10-02.
Missing evidence is not zero. Higher reasoning effort may cost more, and small margins in rounded scores need not be significant. Full methodology →