LLM leaderboard
Every tracked language model by intelligence, with what it costs and how fast it answers.
ranked by intelligence · 690 models · updated Oct 15 · 401–450
| # | Model | Creator | Intelligence | $/1M in | $/1M out | tok/s |
|---|---|---|---|---|---|---|
| 401 | Gemini 2.5 Flash (Non-reasoning) | 9.90 | $0.3 | $2.5 | 203 | |
| 402 | K2-V2 (High) | Institute of Foundation Models | 9.90 | — | — | — |
| 403 | GPT-5 mini (Minimal) | OpenAI | 9.90 | $0.25 | $2 | 144 |
| 404 | Qwen3 VL 235B A22B Instruct | Alibaba | 9.90 | $0.215 | $1.39 | 31 |
| 405 | Qwen3 30B A3B 2507 (Reasoning) | Alibaba | 9.80 | $0.36 | $1.3 | — |
| 406 | o1-mini | OpenAI | 9.80 | — | — | — |
| 407 | DeepSeek V3 0324 | DeepSeek | 9.70 | $0.24 | $0.9 | 83 |
| 408 | Ling 2.6 Flash | InclusionAI | 9.70 | — | — | — |
| 409 | Qwen3 Next 80B A3B Instruct | Alibaba | 9.60 | $0.15 | $1.1 | 140 |
| 410 | GPT-4.5 (Preview) | OpenAI | 9.60 | — | — | — |
| 411 | Tri-21B-think Preview | Trillion Labs | 9.60 | — | — | — |
| 412 | Qwen3 Coder 30B A3B Instruct | Alibaba | 9.60 | $0.15 | $0.7481 | 156 |
| 413 | Qwen3 235B A22B (Reasoning) | Alibaba | 9.50 | — | — | — |
| 414 | DiffusionGemma 26B A4B | 9.50 | — | — | — | |
| 415 | Qwen3 VL 30B A3B (Reasoning) | Alibaba | 9.50 | $0.5 | $0.5 | — |
| 416 | QwQ 32B | Alibaba | 9.50 | — | — | — |
| 417 | Gemma 4 12B (Non-reasoning) | 9.40 | $0.1 | $0.3 | 111 | |
| 418 | Gemini 2.0 Flash Thinking Experimental (Jan '25) | 9.40 | — | — | — | |
| 419 | Mistral Large 3 | Mistral | 9.30 | $0.5 | $1.5 | 76 |
| 420 | Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) | 9.30 | $0.1 | $0.4 | — | |
| 421 | Llama 4 Maverick | Meta | 9.30 | $0.25 | $0.87 | 57 |
| 422 | Mistral Medium 3.1 | Mistral | 9.20 | — | — | — |
| 423 | Ling-1T | InclusionAI | 9.20 | — | — | — |
| 424 | Motif-2-12.7B-Reasoning | Motif Technologies | 9.20 | — | — | — |
| 425 | Nova Premier | Amazon | 9.20 | — | — | — |
| 426 | Qwen3 Coder Next | Alibaba | 9.20 | $0.5 | $1.2 | 66 |
| 427 | Granite 4.2 3B | IBM | 9.10 | $0.03 | $0.12 | 220 |
| 428 | Magistral Medium 1 | Mistral | 9.10 | — | — | — |
| 429 | Solar Pro 2 (Preview) (Reasoning) | Upstage | 9.10 | — | — | — |
| 430 | Mistral Small 4 (Non-reasoning) | Mistral | 9.00 | $0.15 | $0.6 | 146 |
| 431 | gpt-oss-20b (High) | OpenAI | 9.00 | $0.07 | $0.18 | 220 |
| 432 | GPT-4o (March 2025, chatgpt-4o-latest) | OpenAI | 9.00 | — | — | — |
| 433 | Mistral Medium 3 | Mistral | 9.00 | $0.4 | $2 | 45 |
| 434 | Tri-21B-Think | Trillion Labs | 9.00 | — | — | — |
| 435 | Devstral Medium | Mistral | 9.00 | — | — | — |
| 436 | K2-V2 (Medium) | Institute of Foundation Models | 9.00 | — | — | — |
| 437 | Llama Nemotron Super 49B v1.5 (Reasoning) | NVIDIA | 9.00 | — | — | — |
| 438 | Claude 3.5 Haiku | Anthropic | 8.90 | — | — | — |
| 439 | Llama 3.3 Nemotron Super 49B v1 (Reasoning) | NVIDIA | 8.90 | — | — | — |
| 440 | NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) | NVIDIA | 8.90 | $0.05 | $0.2 | 233 |
| 441 | Gemini 2.0 Flash (Feb '25) | 8.90 | — | — | — | |
| 442 | Gemma 4 E4B (Reasoning) | 8.90 | $0.02 | $0.1 | 44 | |
| 443 | Qwen3 4B 2507 (Reasoning) | Alibaba | 8.80 | — | — | — |
| 444 | Sarvam 105B (High) | Sarvam | 8.80 | $0.042 | $0.17 | — |
| 445 | MiniCPM5-1B (Reasoning) | OpenBMB | 8.80 | — | — | — |
| 446 | Sonar Reasoning | Perplexity | 8.70 | — | — | — |
| 447 | Gemini 2.5 Flash Preview (Non-reasoning) | 8.70 | — | — | — | |
| 448 | Nova 2.0 Lite (Non-reasoning) | Amazon | 8.70 | $0.33 | $2.75 | 169 |
| 449 | Claude 3 Opus | Anthropic | 8.70 | $15 | $75 | — |
| 450 | Gemini 2.0 Pro Experimental (Feb '25) | 8.70 | — | — | — |
what intelligence means
A composite of nine independent evaluations covering reasoning, coding, agentic work and knowledge. Higher is better. It is versioned, so scores are comparable within a version rather than across all time.