A task with its own rules.
Independently evaluated automation and agentic workflow benchmark from Artificial Analysis.
- Organisation
- Artificial Analysis
- Version
- Current / rolling
Loading benchmark header
Loading benchmark registry
Agents / Benchmark profile
Independently evaluated automation and agentic workflow benchmark from Artificial Analysis.
Observed results
20 ranked models · higher is better · labels show rank and score
| Model | Rank | Model ID | Provider | Score | Unit |
|---|---|---|---|---|---|
| Kimi K3 | #1 | kimi-k3 | Moonshot AI | 52.7 | percent |
| Grok 4.5 | #2 | grok-4-5 | xAI | 51.4 | percent |
| GPT-5.6 Sol | #3 | gpt-5-6-sol | OpenAI | 51.2 | percent |
| Gemini 3.6 Flash | #4 | gemini-3-6-flash | 51.1 | percent | |
| Claude Fable 5 | #5 | claude-fable-5 | Anthropic | 48.6 | percent |
| Claude Opus 4.8 | #6 | claude-opus-4-8 | Anthropic | 48.5 | percent |
| GLM-5.3 | #7 | glm-5-3 | Z.AI | 48.2 | percent |
| GPT-5.6 Terra | #8 | gpt-5-6-terra | OpenAI | 45.6 | percent |
| Muse Spark 1.1 | #9 | muse-spark-1-1 | Meta | 42.8 | percent |
| Gemini 3.5 Flash | #10 | gemini-3-5-flash | 42.6 | percent | |
| GPT-5.6 Luna | #11 | gpt-5-6-luna | OpenAI | 42.2 | percent |
| GPT-5.5 | #12 | gpt-5-5 | OpenAI | 42.1 | percent |
| Claude Sonnet 5 | #13 | claude-sonnet-5 | Anthropic | 39.2 | percent |
| Gemini 3.1 Pro Preview | #14 | gemini-3-1-pro-preview | 37.5 | percent | |
| Gemini 3.5 Flash-Lite | #15 | gemini-3-5-flash-lite | 32.7 | percent | |
| GLM-5.2 | #16 | glm-5-2 | Z.AI | 27.8 | percent |
| Qwen3.7-Max | #17 | qwen-3-7-max | Alibaba Cloud | 25.6 | percent |
| Kimi K2.7 Code | #18 | kimi-k2-7-code | Moonshot AI | 22.5286 | percent |
| Kimi K2.6 | #19 | kimi-k2-6 | Moonshot AI | 19.5527 | percent |
| Qwen3.5 397B A17B | #20 | qwen3-5-397b | Alibaba Cloud | 12.1956 | percent |
| Nemotron 3 Ultra | #21 | nemotron-3-ultra | NVIDIA | 5.6706 | percent |
One best compatible score per canonical product · higher is better
| Rank | Model | Weights | Evidence | Score |
|---|---|---|---|---|
| 01 | Kimi K3Moonshot AI | Open weights | Direct source result | 52.7% |
| 02 | Grok 4.5xAI | Closed weights | Source carrier | 51.4% |
| 03 | GPT-5.6 SolOpenAI | Closed weights | Source carrier | 51.2% |
| 04 | Gemini 3.6 FlashGoogle | Closed weights | Source carrier | 51.1% |
| 05 | Claude Fable 5Anthropic | Closed weights | Source carrier | 48.6% |
| 06 | Claude Opus 4.8Anthropic | Closed weights | Source carrier | 48.5% |
| 07 | GLM-5.3Z.AI | Open announced | Direct source result | 48.2% |
| 08 | GPT-5.6 TerraOpenAI | Closed weights | Source carrier | 45.6% |
| 09 | Muse Spark 1.1Meta | Closed weights | Direct source result | 42.8% |
| 10 | Gemini 3.5 FlashGoogle | Closed weights | Source carrier | 42.6% |
Each distinct published measurement is retained. Same-snapshot canonical and configuration projections appear once.
| Published model / configuration | Score | Evidence & protocol | Source & dates |
|---|---|---|---|
GLM-5.3 (max)GLM-5.3Exact identityglm-5-3-max Canonical product: glm-5-3 | 48.2% | Direct source resultprovider-reportedVersion & system1.0.6 Z.AI GLM-5.3 official comparison table | GLM-5.3: Frontier Coding with Emergent Cyber CapabilitiesObserved Checked |
Kimi K3 as published by Z.AIKimi K3Exact identitykimi-k3-max Canonical product: kimi-k3 | 46.7% | Relative comparisonprovider-reportedVersion & system1.0.6 Z.AI GLM-5.3 official comparison table | GLM-5.3: Frontier Coding with Emergent Cyber CapabilitiesObserved Checked |
Claude Fable 5 w/ fallback as published by Z.AIClaude Fable 5Exact identityclaude-fable-5-max Canonical product: claude-fable-5 | 46.2% | Relative comparisonprovider-reportedVersion & system1.0.6 Z.AI GLM-5.3 official comparison table | GLM-5.3: Frontier Coding with Emergent Cyber CapabilitiesObserved Checked |
GPT-5.6 Sol as published by Z.AIGPT-5.6 SolExact identitygpt-5-6-sol-max Canonical product: gpt-5-6-sol | 45.8% | Relative comparisonprovider-reportedVersion & system1.0.6 Z.AI GLM-5.3 official comparison table | GLM-5.3: Frontier Coding with Emergent Cyber CapabilitiesObserved Checked |
DeepSeek V4 Pro 0813 as published by Z.AIDeepSeek V4 Pro 0813Exact identitydeepseek-v4-pro-0813-max Canonical product: deepseek-v4-pro-0813 | 43.2% | Relative comparisonprovider-reportedVersion & system1.0.6 Z.AI GLM-5.3 official comparison table | GLM-5.3: Frontier Coding with Emergent Cyber CapabilitiesObserved Checked |
Claude Opus 4.8 as published by Z.AIClaude Opus 4.8Exact identityclaude-opus-4-8-max Canonical product: claude-opus-4-8 | 41% | Relative comparisonprovider-reportedVersion & system1.0.6 Z.AI GLM-5.3 official comparison table | GLM-5.3: Frontier Coding with Emergent Cyber CapabilitiesObserved Checked |
Qwen3.8 Max as published by Z.AIQwen3.8 MaxExact identityqwen-3-8-max-xhigh Canonical product: qwen-3-8-max | 39.8% | Relative comparisonprovider-reportedVersion & system1.0.6 Z.AI GLM-5.3 official comparison table | GLM-5.3: Frontier Coding with Emergent Cyber CapabilitiesObserved Checked |
GLM-5.2 as published by Z.AIGLM-5.2Exact identityglm-5-2-max Canonical product: glm-5-2 | 26.2% | Relative comparisonprovider-reportedVersion & system1.0.6 Z.AI GLM-5.3 official comparison table | GLM-5.3: Frontier Coding with Emergent Cyber CapabilitiesObserved Checked |
Exact BenchLM registry variant Kimi K3; bulk export does not retain a complete upstream harness configuration.Kimi K3Exact identitySource label without a registered configuration ID Canonical product: kimi-k3 | 52.7% | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Grok 4.5; bulk export does not retain a complete upstream harness configuration.Grok 4.5Exact identitySource label without a registered configuration ID Canonical product: grok-4-5 | 51.4% | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
From result to context
Independently evaluated automation and agentic workflow benchmark from Artificial Analysis.
The summary shows one best compatible source result per canonical product. Versions, effort settings and execution systems remain attached to the underlying records.
Scores from different versions or harnesses may not be interchangeable. The published source rows preserve those distinctions and their original units. A source result is not automatically an input to a current index.
This catalogue entry preserves available source evidence. Current indices admit only their specifically reviewed tracks and configurations.
Contamination risk: Unknown. Lifecycle: Active.