Highest index score
80.7
Claude Fable 5.1 (Xhigh, Default Fallback)AI model benchmarks
Compare independent benchmark scores and API prices to find the right models for your work.
Artificial Analysis via OpenRouter100 modelsSnapshot
Model comparison
Top 10 by coding indexLowest input price
$0.825
Gemini 3.7 Flash (High) (+1 tied)Lowest output price
$3.45
Qwen3.8 Max (0902)Summary cards and bars compare this top 10 only. Index scores are not percentages.
Cost efficiency
71 model configurationsIndex score vs. input price
Each point is a model configuration. Toward the upper left means a higher score for a lower input price.
- Anthropic
- OpenAI
- Qwen
- xAI
- Meta
- z-ai
- moonshotai
- DeepSeek
- xiaomi
- tencent
- minimax
- inclusionai
- thinkingmachines
- upstage
- nvidia
- Mistral
- cohere
- ibm-granite
- Input-price frontier
1 free model is outside this logarithmic scale. Switch to Linear to include it.
The dashed frontier connects models with a higher score than every cheaper model, including free models in that comparison. It considers input pricing only; output prices and your workload also affect total cost. Equal spacing on this logarithmic price scale represents equal price ratios.
29 models are omitted from the scatter because this index score or input price is not reported.
View chart data
| Model configuration | Coding index | Input price | Output price |
|---|---|---|---|
| Claude Fable 5.1 (Xhigh, Default Fallback) | 80.7 | $5.00 | $25.00 |
| GPT-5.6 Sol (Xhigh) | 78.3 | $4.00 | $20.00 |
| Claude Opus 5 (Max) | 78 | $5.50 | $27.50 |
| GPT-6 Astra (Max) | 76.9 | $10.00 | $50.00 |
| GPT-5.6 Terra (Max) | 76.7 | $4.00 | $24.00 |
| Claude Fable 5 (Max, Opus 4.8 Fallback) | 76.5 | $10.00 | $50.00 |
| Gemini 3.8 Flash (High) | 76.3 | $0.825 | $4.125 |
| Qwen3.8 Max (0902) | 76.2 | $1.15 | $3.45 |
| Gemini 3.7 Flash (High) | 76.1 | $0.825 | $4.125 |
| Grok 4.6 (Xhigh) | 75.9 | $1.60 | $4.80 |
| Muse Spark 1.3 (Max) | 75.8 | $1.25 | $4.25 |
| GPT-5.5 (Xhigh) | 74.9 | $2.50 | $15.00 |
| GLM-5.3 (Max) | 74.8 | $0.527 | $1.075 |
| Claude Opus 4.8 (Max) | 74.3 | $10.00 | $50.00 |
| Claude Opus 4.7 (Max) | 73.6 | $5.00 | $25.00 |
| Grok 4.5 (High) | 72.4 | $4.00 | $12.00 |
| Muse Spark 1.2 (Xhigh) | 72.2 | $1.25 | $4.25 |
| Kimi K3 (Low) | 72 | $2.30 | $14.00 |
| Qwen3.8 2.4T A95B | 71.9 | $2.00 | $6.00 |
| Claude Sonnet 5 (Max) | 71.5 | $2.20 | $11.00 |
| GLM-5.3-Flash | 71.5 | $0.15 | $0.50 |
| GPT-5.6 Luna (Max) | 71.4 | $0.20 | $1.20 |
| Muse Spark 1.1 (Xhigh) | 71.3 | $1.25 | $4.25 |
| GPT-5.4 (Xhigh) | 71.1 | $5.00 | $30.00 |
| Gemini 3.5 Flash (High) | 70.1 | $2.70 | $16.20 |
| Gemini 3.6 Flash (High) | 69.2 | $1.35 | $6.75 |
| DeepSeek V4 Flash 0731 (Max) | 69.1 | $0.048 | $0.144 |
| Qwen3.8 Max | 68.9 | Not reported | Not reported |
| DeepSeek V4 Pro 0813 (Max) | 68.8 | $1.98 | $5.94 |
| Gemini 3.1 Pro Preview | 68.8 | $3.60 | $21.60 |
| GLM-5.2 (Max) | 68.8 | $0.527 | $1.075 |
| Qwen3.8 27B (Xhigh) | 68.1 | $0.16 | $2.00 |
| Qwen3.7 Max | 66 | $2.00 | $6.00 |
| DeepSeek V4 Flash Vision (Max) | 65 | $0.44 | $1.32 |
| Claude Sonnet 4.6 (Max) | 63 | $3.00 | $15.00 |
| Kimi K2.6 (Reasoning) | 61.8 | $0.65 | $3.41 |
| Kimi K2.7 Code | 60.8 | $0.7125 | $3.00 |
| MiMo-V2.5-Pro (Reasoning) | 60.2 | $0.435 | $0.87 |
| KAT Coder Pro V2 | 59.5 | Not reported | Not reported |
| Nex-N2-Pro (Based on Qwen3.5-397B-A17B) | 59.1 | Not reported | Not reported |
| Hy3 | 58.8 | $0.18 | $0.60 |
| MiniMax-M3 | 58.6 | $0.224 | $0.88 |
| Ling-3.0-flash-VL | 57 | $0.06 | $0.18 |
| MiMo-V2.5 | 56.8 | $0.40 | $2.00 |
| DeepSeek V4 Flash 0420 (Max) | 56.2 | $0.105 | $0.21 |
| GPT-5.4 mini (Xhigh) | 56.1 | $1.50 | $9.00 |
| GPT-5.4 nano (Xhigh) | 56.1 | $0.10 | $0.625 |
| Qwen3.7 Plus | 55.9 | $0.23 | $0.92 |
| GLM-5.1 (Reasoning) | 55.8 | $1.33 | $4.18 |
| Ling-3.0-flash-Fin | 55.6 | Not reported | Not reported |
| Qwen3.6 Plus | 54.5 | $0.325 | $1.95 |
| Qwen3.6 27B (Reasoning) | 53.7 | $0.20 | $3.00 |
| Inkling Small | 52.9 | $0.36 | $0.96 |
| Solar Pro 4 | 52.7 | $0.15 | $0.60 |
| MiniMax-M2.7 | 52.6 | $0.21 | $0.84 |
| Claude 4.5 Sonnet (Reasoning) | 52.1 | $3.00 | $15.00 |
| Inkling (Xhigh) | 52.1 | $1.00 | $4.05 |
| Grok Build 0.1 0616 | 51.5 | $2.00 | $4.00 |
| Ling 3.0 Flash | 50.6 | $0.021 | $0.063 |
| MiMo-V2-Flash (Non-reasoning) | 49.8 | Not reported | Not reported |
| GPT-5.1 (High) | 49.4 | $2.50 | $20.00 |
| Gemini 3.5 Flash-Lite | 49.3 | $0.54 | $4.50 |
| Nemotron 3 Ultra 550B A55B (Reasoning) | 49.3 | $0.40 | $1.76 |
| Muse Glimmer (High) | 49 | $0.24 | $0.96 |
| Qwen3.5 397B A17B (Reasoning) | 48.2 | $0.60 | $3.60 |
| Mistral Medium 3.5 | 46.9 | $0.75 | $3.75 |
| Kimi K2.5 (Reasoning) | 46.8 | $0.60 | $3.00 |
| Claude 4.5 Haiku (Reasoning) | 43.9 | $1.10 | $5.50 |
| Gemma 4 31B (Reasoning) | 43.4 | $0.34 | $0.10 |
| North Mini Code | 36.5 | $0.00 | $0.00 |
| Gemini 3.1 Flash-Lite | 34.7 | $0.45 | $2.70 |
| gpt-oss-120b (High) | 30.4 | $0.15 | $0.75 |
| Command A+ | 27.8 | $0.30 | $1.50 |
| Nemotron 3.5 Lightning | 26.8 | $0.05 | $0.20 |
| Mistral Small 4 (Reasoning) | 26.6 | $0.165 | $0.66 |
| Granite 4.2 8B | 22.4 | $0.06 | $0.25 |
Leaderboard
Explore benchmark scores and API prices. Shortlist up to three models to compare.
Top 10 of 100 models
Select 2–3 to compare
| Position# | Model | Coding index | API pricing / 1M tokens | Add to comparison |
|---|---|---|---|---|
| 1 | Claude Fable 5.1 (Xhigh, Default Fallback) | Coding 80.7 | In $5.00 / Out $25.00 / 1M tokens | |
| 2 | GPT-5.6 Sol (Xhigh) | Coding 78.3 | In $4.00 / Out $20.00 / 1M tokens | |
| 3 | Claude Opus 5 (Max) | Coding 78.0 | In $5.50 / Out $27.50 / 1M tokens | |
| 4 | GPT-6 Astra (Max) | Coding 76.9 | In $10.00 / Out $50.00 / 1M tokens | |
| 5 | GPT-5.6 Terra (Max) | Coding 76.7 | In $4.00 / Out $24.00 / 1M tokens | |
| 6 | Claude Fable 5 (Max, Opus 4.8 Fallback) | Coding 76.5 | In $10.00 / Out $50.00 / 1M tokens | |
| 7 | Gemini 3.8 Flash (High) | Coding 76.3 | In $0.83 / Out $4.13 / 1M tokens | |
| 8 | Qwen3.8 Max (0902) | Coding 76.2 | In $1.15 / Out $3.45 / 1M tokens | |
| 9 | Gemini 3.7 Flash (High) | Coding 76.1 | In $0.83 / Out $4.13 / 1M tokens | |
| 10 | Grok 4.6 (Xhigh) | Coding 75.9 | In $1.60 / Out $4.80 / 1M tokens |
Prices in USD. Missing values are “Not reported.” Configuration labels are preserved from the source.
Methodology & sources
Source: Artificial Analysis (artificialanalysis.ai) via OpenRouter (openrouter.ai/rankings).
Licensed under CC BY 4.0. View the license. Artificial Analysis source.
How to read these results
Each view uses one Artificial Analysis index. Intelligence, coding and agentic scores measure different evaluations. They are not percentages and are not combined with popularity or individual test accuracies. Configuration labels are preserved from the source.
Prices are USD per million input or output tokens. The cost-efficiency chart compares input prices only; output prices and your workload also affect total cost. Shortlist models to estimate token charges for the same workload. Actual costs depend on tokens consumed and provider rates.
These general benchmarks do not measure CRE underwriting accuracy. Test a shortlist on the same rent roll, T-12 and lease examples, checking extraction, arithmetic and cited evidence against known answers before using it for live work.
The snapshot timestamp identifies the source data snapshot, not when every model was evaluated.