Agent Index v1.0
The Shogo Agent Index
A weighted index of 17 benchmarks that measure what agents actually do. 92 models are ranked: 44 have enough measured results to be Supported; the rest are Estimated from at least two measured agentic results plus overall capability. 147 more models have a capability score but too few agentic results to rank yet. Full methodology.
| Model | Agent Index | Coding | Long-hzn | Know. work | Comp. use | Sec/ctx | Measured | Agent $/M | Context |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.2 AnthropicSupported | 76.4 71.7–81.2 | 86 | 78 | 67 | 77 | 65 | 32% | $3.21 | 1M |
| Gemini 4 Carbon GoogleSupported | 73.6 67.2–80 | 82 | 80 | 63 | 68 | 63 | 27% | $0.84 | 1M |
| Claude Opus 5.5 AnthropicSupported | 70.9 64.8–76.9 | 81 | 76 | 58 | 66 | 62 | 32% | $1.69 | 1M |
| GPT-6 Astra OpenAISupported | 70.9 66.5–75.4 | 80 | 80 | 56 | 67 | 63 | 38% | $4.62 | 1.1M |
| GPT-6.1 Sol OpenAIEstimated | 70.0 62.2–77.7 | 80 | 78 | 54 | 66 | 62 | 18% | $0.84 | 1.1M |
| Gemini 4 Argon GoogleSupported | 69.5 62.9–76.2 | 77 | 78 | 59 | 61 | 61 | 32% | $0.84 | 1M |
| Gemini 4 Hydrogen GoogleEstimated | 69.4 61.8–77.1 | 78 | 78 | 58 | 61 | 61 | 23% | $0.63 | 1M |
| GPT-6.1 Terra OpenAIEstimated | 69.0 60.5–77.5 | 79 | 74 | 56 | 63 | 62 | 14% | $0.42 | 1.1M |
| Claude Sonnet 5.5 AnthropicEstimated | 69.0 61.3–76.7 | 79 | 75 | 57 | 61 | 61 | 23% | $0.84 | 1M |
| Claude Fable 5.1 AnthropicSupported | 68.2 62.7–73.7 | 80 | 71 | 55 | 62 | 61 | 36% | $4.01 | 1M |
| Claude Opus 5 AnthropicSupported | 65.4 59.8–71 | 74 | 74 | 52 | 56 | 59 | 39% | $2.31 | 1M |
| Claude Fable 5 AnthropicSupported | 64.1 59–69.3 | 74 | 69 | 52 | 55 | 59 | 38% | $4.62 | 1M |
| GPT-6 Sol OpenAIEstimated | 63.6 54.2–73 | 72 | 76 | 48 | 54 | 59 | 14% | $0.92 | 1.1M |
| GPT-5.6 Sol OpenAISupported | 61.8 57.1–66.5 | 71 | 72 | 46 | 53 | 58 | 43% | $1.85 | 1.1M |
| Muse Wonder MetaEstimated | 60.9 51.9–69.9 | 68 | 70 | 50 | 50 | 57 | 22% | $1.69 | 1M |
| GPT-5.6 Terra OpenAIEstimated | 58.8 50.7–66.9 | 66 | 69 | 47 | 48 | 56 | 24% | $1.02 | 1.1M |
| DeepSeek V4.1 Flash 1017 DeepSeek· openEstimated | 57.6 44.4–70.8 | 63 | 66 | 49 | 45 | 54 | 12% | $0.050 | 1M |
| Claude Haiku 5.5 AnthropicEstimated | 57.5 48.4–66.5 | 67 | 62 | 46 | 47 | 55 | 23% | $0.050 | 1M |
| GPT-5.5 OpenAISupported | 56.7 52.5–61 | 63 | 67 | 46 | 43 | 55 | 60% | $2.55 | 1.1M |
| Claude Opus 4.8 AnthropicSupported | 56.3 50.9–61.8 | 63 | 66 | 43 | 47 | 55 | 44% | $2.31 | 1M |
| Gemini 3.8 Flash GoogleSupported | 56.2 48.7–63.7 | 63 | 64 | 47 | 44 | 53 | 34% | $0.35 | 1M |
| Grok 4.6 xAISupported | 56.2 48.3–64 | 61 | 68 | 47 | 42 | 52 | 29% | $0.98 | 500K |
| Gemini 3.7 Flash GoogleEstimated | 55.7 44.2–67.1 | 61 | 64 | 48 | 43 | 53 | 24% | $0.35 | 1M |
| Inkling 2 Small thinkingmachines· openEstimated | 55.2 42.3–68.2 | 62 | 66 | 42 | 44 | 54 | 13% | $0.14 | 1M |
| GLM-5.3 Z.ai (Zhipu)· openSupported | 55.2 47.7–62.7 | 62 | 68 | 43 | 40 | 51 | 33% | $0.61 | 1M |
| Kimi K3 Moonshot AI· openSupported | 54.9 47.3–62.5 | 63 | 65 | 42 | 43 | 53 | 29% | $1.39 | 1M |
| Grok 4.7 xAIEstimated | 54.8 45.1–64.5 | 58 | 69 | 47 | 39 | 50 | 23% | $0.98 | 500K |
| Muse Spark 1.3 MetaEstimated | 54.7 41.6–67.7 | 60 | 64 | 45 | 43 | 53 | 17% | $0.030 | 1M |
| Claude Opus 4.7 AnthropicSupported | 54.6 47.7–61.5 | 60 | 69 | 41 | 44 | 52 | 44% | $2.31 | 1M |
| Qwen3.8 Max Preview Alibaba (Qwen)Estimated | 53.6 41.7–65.5 | 58 | 63 | 46 | 41 | 52 | 19% | Free | 1M |
| Claude Opus 4.6 AnthropicSupported | 53.2 47.9–58.6 | 57 | 67 | 41 | 39 | 57 | 64% | $2.31 | 1M |
| Claude Sonnet 5 AnthropicSupported | 52.4 45.1–59.8 | 57 | 65 | 43 | 40 | 51 | 28% | $0.92 | 1M |
| GPT-5.4 OpenAISupported | 51.6 47.2–56.1 | 57 | 61 | 40 | 42 | 54 | 64% | $1.27 | 1.1M |
| GPT-5.6 Luna OpenAIEstimated | 51.4 42.8–59.9 | 59 | 61 | 39 | 40 | 51 | 24% | $0.10 | 1.1M |
| DeepSeek V4.1 Flash DeepSeek· openEstimated | 51.2 37.1–65.2 | 57 | 62 | 39 | 40 | 51 | 13% | $0.12 | 1M |
| Grok 4.5 xAIEstimated | 49.4 40.9–57.9 | 54 | 59 | 42 | 36 | 48 | 24% | $0.81 | 500K |
| GPT-5.3 Codex OpenAISupported | 48.4 38.5–58.4 | 53 | 62 | 37 | 35 | 47 | 32% | $1.06 | 400K |
| GLM-5.3-Flash Z.ai (Zhipu)· openSupported | 48.3 36.5–60 | 54 | 57 | 40 | 34 | 47 | 27% | $0.16 | 1M |
| Gemini 3.6 Flash GoogleEstimated | 48.3 35.5–61.2 | 53 | 58 | 39 | 37 | 49 | 14% | $0.35 | 1M |
| Muse Spark 1.1 MetaEstimated | 48.3 39.3–57.2 | 53 | 64 | 34 | 36 | 48 | 20% | $0.50 | 1M |
| Muse Spark 1.2 MetaEstimated | 48.2 35.8–60.6 | 53 | 58 | 38 | 37 | 49 | 19% | $0.50 | 1M |
| GLM-5.2 Z.ai (Zhipu)· openSupported | 47.3 39.3–55.3 | 49 | 66 | 37 | 33 | 45 | 32% | $0.61 | 1M |
| Gemini 3.5 Flash GoogleSupported | 47.3 39–55.6 | 52 | 62 | 33 | 37 | 49 | 28% | $0.76 | 200K |
| GPT-5.2 OpenAISupported | 46.4 39.5–53.2 | 49 | 59 | 37 | 36 | 46 | 58% | $0.96 | 400K |
| Gemini 3.1 Pro Preview GoogleSupported | 46.0 41.6–50.5 | 47 | 59 | 36 | 39 | 49 | 64% | $1.02 | 1M |
| Claude Opus 4.5 (latest) AnthropicSupported | 46.0 41.5–50.6 | 47 | 61 | 37 | 30 | 52 | 67% | $2.31 | 200K |
| Claude Sonnet 4.6 AnthropicSupported | 44.9 39.6–50.3 | 43 | 63 | 38 | 34 | 45 | 51% | $1.39 | 1M |
| Gemini 3 Pro Preview GoogleSupported | 44.7 37.9–51.6 | 48 | 60 | 34 | 33 | 43 | 58% | $2.48 | 1M |
| Grok 4.20 (Non-Reasoning) xAIEstimated | 43.9 33.3–54.5 | 45 | 59 | 34 | 32 | 45 | 19% | $0.46 | 2M |
| Kimi K2.6 Moonshot AI· openEstimated | 43.7 32.3–55.1 | 46 | 61 | 33 | 29 | 43 | 20% | $0.46 | 262K |
| Gemini 3 Flash Preview GoogleSupported | 43.7 34.9–52.5 | 46 | 57 | 35 | 32 | 44 | 31% | $0.21 | 1M |
| GLM-5.1 Z.ai (Zhipu)· openEstimated | 42.5 32.6–52.4 | 43 | 59 | 34 | 29 | 42 | 22% | $0.46 | 200K |
| Kimi K2.7 Code Moonshot AI· openEstimated | 42.1 33.1–51.2 | 43 | 59 | 33 | 30 | 42 | 20% | $0.96 | 262K |
| DeepSeek V4 Pro DeepSeek· openEstimated | 40.7 29.3–52.1 | 43 | 55 | 32 | 28 | 41 | 14% | $0.50 | 1M |
| Qwen3.6 Max Preview Alibaba (Qwen)Estimated | 40.5 29.2–51.9 | 42 | 56 | 31 | 27 | 40 | 14% | $1.08 | 262K |
| GPT-5.1 Codex Max OpenAIEstimated | 39.6 26.4–52.9 | 43 | 48 | 32 | 28 | 41 | 18% | $0.67 | 400K |
| GPT-5.1 OpenAISupported | 38.8 30.4–47.3 | 40 | 49 | 32 | 29 | 44 | 36% | $0.69 | 400K |
| Claude Sonnet 4.5 (latest) AnthropicSupported | 38.7 34.6–42.8 | 38 | 54 | 32 | 27 | 39 | 62% | $1.39 | 200K |
| Qwen3.6 Plus Alibaba (Qwen)Estimated | 38.0 27.1–48.9 | 36 | 57 | 30 | 26 | 39 | 19% | Free | 1M |
| GPT-5 OpenAISupported | 37.8 27.8–47.8 | 40 | 47 | 31 | 27 | 40 | 47% | $0.76 | 400K |
| MiniMax-M3 MiniMax· openEstimated | 36.7 26.5–46.8 | 37 | 49 | 31 | 24 | 37 | 20% | $0.15 | 524K |
| GLM-5 Z.ai (Zhipu)· openSupported | 36.5 27.7–45.4 | 38 | 54 | 27 | 21 | 35 | 27% | $0.33 | 205K |
| Kimi K2.5 Moonshot AI· openSupported | 36.5 28.3–44.8 | 38 | 45 | 30 | 28 | 39 | 31% | $0.31 | 262K |
| Inkling thinkingmachines· openEstimated | 35.8 23–48.6 | 38 | 44 | 30 | 25 | 38 | 13% | $0.79 | 262K |
| Qwen3.5 Plus Alibaba (Qwen)Estimated | 32.7 21.5–44 | 36 | 37 | 28 | 23 | 37 | 11% | $0.20 | 1M |
| Claude Opus 4.1 (latest) AnthropicSupported | 32.1 25.4–38.8 | 34 | 40 | 30 | 19 | 29 | 43% | $5.96 | 197K |
| o3 OpenAISupported | 31.4 22.5–40.2 | 34 | 42 | 27 | 11 | 35 | 43% | $0.97 | 200K |
| Grok 4 xAISupported | 30.9 22.4–39.4 | 32 | 42 | 25 | 22 | 30 | 35% | — | — |
| GPT-5 Mini OpenAIEstimated | 30.4 21.4–39.3 | 32 | 36 | 26 | 21 | 33 | 22% | $0.15 | 264K |
| Kimi K2 Thinking Moonshot AI· openEstimated | 30.3 19.8–40.9 | 32 | 37 | 26 | 20 | 33 | 23% | $0.35 | 262K |
| GLM-4.7 Z.ai (Zhipu)· openEstimated | 30.0 21.3–38.8 | 30 | 47 | 23 | 16 | 29 | 19% | $0.24 | 205K |
| DeepSeek V3.2 DeepSeek· openSupported | 30.0 22.1–37.8 | 32 | 41 | 24 | 18 | 29 | 27% | $0.16 | 128K |
| o4-mini OpenAIEstimated | 29.8 19.2–40.4 | 31 | 39 | 24 | 19 | 32 | 21% | $0.53 | 200K |
| MiniMax-M2.5 MiniMax· openEstimated | 28.4 19.5–37.2 | 32 | 34 | 24 | 17 | 27 | 19% | Free | 197K |
| Claude-Opus-4 AnthropicSupported | 27.9 20.4–35.4 | 29 | 38 | 24 | 16 | 27 | 32% | $5.96 | 193K |
| Claude Haiku 4.5 AnthropicEstimated | 27.1 18.9–35.3 | 30 | 34 | 23 | 15 | 28 | 19% | $0.46 | 200K |
| Qwen3 Coder 480B A35B Alibaba (Qwen)· openEstimated | 26.4 16.9–35.9 | 27 | 36 | 22 | 15 | 27 | 12% | $0.17 | 262K |
| Claude Sonnet 4 AnthropicSupported | 26.2 19.5–33 | 26 | 36 | 23 | 19 | 25 | 28% | $1.20 | 983K |
| Qwen3 Max Alibaba (Qwen)Estimated | 25.7 16.2–35.3 | 27 | 33 | 23 | 15 | 27 | 11% | $0.18 | 262K |
| Kimi K2 0905 Moonshot AI· openEstimated | 25.3 16.2–34.3 | 26 | 34 | 21 | 13 | 25 | 12% | $1.16 | 262K |
| Gemini 2.5 Pro GoogleSupported | 24.5 19.4–29.6 | 27 | 32 | 21 | 13 | 24 | 53% | $0.76 | 1M |
| Claude 3.7 Sonnet AnthropicSupported | 24.2 18.6–29.8 | 25 | 35 | 21 | 15 | 18 | 36% | $1.20 | 197K |
| MiniMax-M2 MiniMax· openEstimated | 23.9 16–31.9 | 26 | 31 | 20 | 12 | 23 | 14% | $0.40 | 400K |
| Gemini 2.5 Flash GoogleEstimated | 23.6 15.5–31.8 | 24 | 33 | 21 | 13 | 24 | 14% | $0.19 | 1M |
| o3-mini OpenAIEstimated | 23.3 14.9–31.6 | 24 | 34 | 21 | 13 | 19 | 9% | $1.13 | 200K |
| GPT OSS 120B OpenAI· openSupported | 22.1 15.7–28.5 | 23 | 31 | 17 | 12 | 24 | 32% | $0.040 | 131K |
| DeepSeek-R1 DeepSeek· openEstimated | 21.1 13.5–28.6 | 21 | 31 | 18 | 10 | 21 | 15% | $0.71 | 80K |
| o1 OpenAIEstimated | 16.7 11.7–21.7 | 16 | 28 | 16 | 6 | 11 | 15% | $15.90 | 200K |
| Claude-Sonnet-3.5 AnthropicEstimated | 14.8 10.9–18.8 | 14 | 25 | 14 | 4 | 14 | 19% | $1.20 | 189K |
| GPT-4o (2024-08-06) OpenAISupported | 12.2 10–14.5 | 10 | 22 | 12 | 2 | 11 | 34% | $1.68 | 128K |
| Qwen2.5-72B Alibaba (Qwen)· openEstimated | 12.1 8.5–15.7 | 11 | 20 | 12 | 2 | 9 | 14% | — | — |
| Claude 3 Opus AnthropicEstimated | 11.0 7.9–14.1 | 11 | 16 | 12 | 2 | 10 | 15% | — | — |
Tick models to compare them side by side. Pillar scores in white include measured results; grey ones are fully estimated. Shaded band = 95% range.
What’s in the index
Agentic coding
35%Fixing real repos, working in a terminal and shipping multi-file changes without a human in the loop.
- SWE-bench Verified32 models · 8%
- Terminal-Bench 2.044 models · 8%
- DeepSWE26 models · 6%
- FrontierSWE25 models · 5%
- CursorBench22 models · 4%
- GSO-Bench30 models · 4%
Long-horizon autonomy
20%Staying on task for hours: long software tasks, running a business, training a model end to end.
- METR Time Horizons35 models · 10%
- Vending-Bench 268 models · 6%
- PostTrainBench21 models · 4%
Knowledge-work agents
25%Professional deliverables graded by experts: banking, consulting, law, research reports, paid freelance jobs.
- APEX-Agents62 models · 8%
- GDPval11 models · 7%
- Remote Labor Index18 models · 5%
- DeepResearch Bench24 models · 5%
Computer use
10%Operating a real desktop and browser through screenshots, mouse and keyboard.
- OSWorld 2.09 models · 6%
- OSWorld9 models · 4%