Model Comparison
Agnes 2.5 Pro Beta vs Deepseek V4 Pro
Agnes 2.5 Pro Beta ranks #74 on the AI IQ leaderboard with an estimated IQ of 110, while Deepseek V4 Pro ranks #31 on the AI IQ leaderboard with an estimated IQ of 123. The table below puts the two models side by side across the seven capability dimensions, emotional reasoning, cost, speed, and context window.
Where They Sit on the IQ Bell Curve
Both models highlighted on the standard normal IQ distribution of every tracked model
| Agnes 2.5 Pro BetaWorld (Other) | Deepseek V4 ProDeepSeek | |
|---|---|---|
| Rank | #74 | #31 |
| IQ | 110 | 123 |
| Abstract Reasoning | 96 | 109 |
| Mathematical Reasoning | 104 | 132 |
| Academic Reasoning | 127 | 130 |
| Programmatic Reasoning | 98 | 129 |
| Computer Use | 108 | 123 |
| Reliability | 116 | 118 |
| Knowledge Work | 121 | 124 |
| Emotional Reasoning | — | 118 |
| Effective Cost / 1M Tokens | $0.82 | $7.02 |
| Sticker Price / 1M I/O Tokens | $0.40 | $5.28 |
| Speed | 116 tok/s | 79 tok/s |
| Context Window | 1M | 1M |
| Released | 2026-08-26 | 2026-04-24 |
| Open Weights | No | Yes |
More comparisons
- Agnes 2.5 Pro Beta vs Fable 5.1
- Agnes 2.5 Pro Beta vs Gemini 4 Argon
- Agnes 2.5 Pro Beta vs Glm 5.3
- Agnes 2.5 Pro Beta vs GPT 6 Astra
- Agnes 2.5 Pro Beta vs Grok 4.7
- Agnes 2.5 Pro Beta vs Kimi K3
- Agnes 2.5 Pro Beta vs Mimo V2.6 Pro
- Agnes 2.5 Pro Beta vs Minimax M3
- Agnes 2.5 Pro Beta vs Muse Wonder Full
- Agnes 2.5 Pro Beta vs Qwen3.8 Max 0902
- Deepseek V4 Pro vs Fable 5.1
- Deepseek V4 Pro vs Gemini 4 Argon
- Deepseek V4 Pro vs Glm 5.3
- Deepseek V4 Pro vs GPT 6 Astra
- Deepseek V4 Pro vs Grok 4.7
- Deepseek V4 Pro vs Kimi K3
- All comparisons