Add to ChromeModel leaderboard
The top-ranked models across intelligence, price, speed, and more.
Fastest models
Data sourced from artificialanalysis.ai| # | Model | Speed (tok/s) | Latency (s) | Score |
|---|---|---|---|---|
| #1 |  Gemini 2.5 Flash-Lite (Non-reasoning) Google | 232 | 0.31 | 177 |
| #2 |  Mercury 2 Inception | 835 | 3.93 | 169 |
| #3 |  Nemotron 3 Nano Omni 30B A3B Reasoning NVIDIA | 323 | 1.03 | 159 |
| #4 | Nemotron 3.5 Lightning NVIDIA | 302 | 1.16 | 140 |
| #5 | Gemini 2.5 Flash (Reasoning) Google | 200 | 0.46 | 137 |
| #6 | NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) NVIDIA | 225 | 0.89 | 119 |
| #7 |  Step 3.5 Flash 2603 Stepfun | 214 | 1.14 | 100 |
| #8 |  Mistral Small 4 (Non-reasoning) Mistral | 160 | 0.8 | 89 |
| #9 |  gpt-oss-120b (low) OpenAI | 161 | 0.88 | 86 |
| #10 |  Trinity Large Thinking Arcee AI | 197 | 1.38 | 83 |
Best value models
Data sourced from artificialanalysis.ai| # | Model | Price ($/M) | Intelligence | Score |
|---|---|---|---|---|
| #1 | Ling 3.0 Flash Inclusionai | $0.04 | 37.8 | 900 |
| #2 | Ling 2.6 Flash Inclusionai | $0.02 | 14.2 | 710 |
| #3 |  Solar Pro 4 Upstage | $0.07 | 41.6 | 555 |
| #4 |  DeepSeek V4 Flash 0731 (Reasoning, Max Effort) DeepSeek | $0.13 | 51.8 | 398 |
| #5 | DeepSeek V4 Flash 0423 DeepSeek | $0.12 | 42.1 | 352 |
| #6 | MiMo-V2.5 Xiaomi | $0.21 | 38 | 181 |
| #7 | gpt-oss-20b (low) OpenAI | $0.08 | 14.4 | 180 |
| #8 | Nemotron 3.5 Lightning NVIDIA | $0.14 | 23.6 | 169 |
| #9 |  Qwen3.5 9B (Non-reasoning) Qwen | $0.13 | 20.6 | 165 |
| #10 | gpt-oss-120b (low) OpenAI | $0.1 | 14.9 | 149 |
Intelligence
artificialanalysis.ai
Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)
Grok 4.6 (high)
GLM-5.3 (max)Qwen3.8 MaxQwen3.8 2.4T A95BClaude Opus 4.8 (Adaptive Reasoning, Max Effort)Claude Opus 4.8 (Adaptive Reasoning, Max Effort)
Muse Spark 1.2 (xhigh)