LLM leaderboard
LLM Leaderboard — Model Rankings by Price & Performance
Independent ranking of 130+ frontier and open-weight language models, scored by Value Score — quality benchmark divided by blended $/1M token cost, normalized across every tracked model. Token usage, list pricing, context window, and 30-day price moves are refreshed daily so you can see which models deliver the most performance per dollar this week.
Last updated: 2026-09-15 · 59 models · sorted by Value Score (highest first)
Value Score formula: Value Score = quality benchmark ÷ blended token cost, normalized across all models. Higher = more performance per dollar.
| # | Model | Provider | Category | Input $/M | Output $/M | Context | Benchmark | Value Score | Tokens | DoD | Price Δ 30d |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 01 | Ministral 8B ministral-8b |
Mistral | Budget | $0.100 | $0.100 | 128K | 58 | 100 High Value | 167B | +22% | 0% |
| 02 | MiMo V2.5 Lite mimo-v2-5-lite |
Xiaomi | Budget | $0.050 | $0.200 | 64K | 58 | 71 Fair Value | 211B | +33% | 0% |
| 03 | DeepSeek V4 Flash deepseek-v4-flash |
DeepSeek | Budget | $0.070 | $0.280 | 128K | 78 | 69 Fair Value | 5.11T | +70% | -30% |
| 04 | DeepSeek V3.2 deepseek-v3-2 |
DeepSeek | Budget | $0.140 | $0.280 | 128K | 75 | 58 Fair Value | 1.09T | -31% | -50% |
| 05 | abab6.5s-chat minimax-abab-6-5s-chat |
MiniMax | Budget | $0.100 | $0.300 | 128K | 60 | 47 Fair Value | 114B | +36% | 0% |
| 06 | Gemini 3 Flash gemini-3-flash |
Budget | $0.100 | $0.400 | 1M | 74 | 46 Fair Value | 454B | +49% | -33% | |
| 07 | Hy3 Lite hy3-lite |
Tencent | Budget | $0.100 | $0.400 | 128K | 64 | 39 Low Value | 165B | +50% | 0% |
| 08 | Kimi K2 Mini kimi-k2-mini |
Moonshot | Budget | $0.100 | $0.400 | 128K | 60 | 37 Low Value | 179B | +35% | 0% |
| 09 | Gemini 2.5 Flash gemini-2-5-flash |
Budget | $0.150 | $0.600 | 1M | 70 | 29 Low Value | 565B | -20% | 0% | |
| 10 | MiniMax M2 minimax-m2 |
MiniMax | Coding | $0.200 | $0.800 | 200K | 74 | 23 Low Value | 253B | +61% | 0% |
| 11 | MiMo V2.5 mimo-v2-5 |
Xiaomi | Open | $0.200 | $0.800 | 128K | 71 | 22 Low Value | 2.67T | +25% | 0% |
| 12 | MiniMax M1 minimax-m1 |
MiniMax | Reasoning | $0.200 | $0.800 | 128K | 68 | 21 Low Value | 187B | -27% | 0% |
| 13 | Llama 4 Maverick llama-4-maverick |
Meta | Open | $0.270 | $0.850 | 1M | 73 | 20 Low Value | 531B | -15% | 0% |
| 14 | DeepSeek V4 Pro deepseek-v4-pro |
DeepSeek | Flagship | $0.270 | $1.10 | 128K | 82 | 18 Low Value | 1.93T | +4% | -10% |
| 15 | Grok 4.1 Fast grok-4-1-fast |
xAI | Long-context | $0.200 | $1.00 | 256K | 72 | 18 Low Value | 771B | -3% | -20% |
| 16 | Grok Code Fast 1 grok-code-fast-1 |
xAI | Coding | $0.200 | $1.00 | 128K | 71 | 18 Low Value | 621B | +101% | 0% |
| 17 | Codestral 25.10 codestral-25-10 |
Mistral | Coding | $0.300 | $0.900 | 32K | 70 | 18 Low Value | 402B | +56% | 0% |
| 18 | MiniMax M3 minimax-m3 |
MiniMax | Reasoning | $0.300 | $1.20 | 1M | 80 | 16 Low Value | 3.62T | +143% | 0% |
| 19 | Grok 3 Mini grok-3-mini |
xAI | Budget | $0.200 | $1.00 | 64K | 62 | 16 Low Value | 220B | -8% | 0% |
| 20 | Kimi K2 Instruct kimi-k2-instruct |
Moonshot | Open | $0.300 | $1.20 | 200K | 72 | 15 Low Value | 685B | +69% | 0% |
| 21 | GPT-5.4 Mini gpt-5-4-mini |
OpenAI | Budget | $0.300 | $1.20 | 400K | 73 | 15 Low Value | 494B | +10% | -10% |
| 22 | MiMo Reasoner mimo-reasoner |
Xiaomi | Reasoning | $0.300 | $1.20 | 128K | 72 | 15 Low Value | 428B | +87% | 0% |
| 23 | MiMo Coder mimo-coder |
Xiaomi | Coding | $0.300 | $1.20 | 128K | 69 | 14 Low Value | 336B | +29% | 0% |
| 24 | Kimi K1.5 Long kimi-k1-5-long |
Moonshot | Long-context | $0.300 | $1.20 | 1M | 66 | 14 Low Value | 323B | +41% | 0% |
| 25 | Hunyuan-Large hunyuan-large |
Tencent | Open | $0.300 | $1.20 | 128K | 67 | 14 Low Value | 171B | +25% | 0% |
| 26 | DeepSeek V4.1 deepseek-v4-1 |
DeepSeek | Flagship | $0.420 | $1.68 | 512K | 85 | 12 Low Value | 2.37T | +111% | 0% |
| 27 | Kimi K2.6 kimi-k2-6 |
Moonshot | Coding | $0.400 | $1.60 | 256K | 76 | 12 Low Value | 967B | 0% | 0% |
| 28 | Kimi Coder kimi-coder |
Moonshot | Coding | $0.400 | $1.60 | 256K | 77 | 12 Low Value | 571B | +77% | 0% |
| 29 | Grok 4 Mini grok-4-mini |
xAI | Budget | $0.300 | $1.50 | 128K | 70 | 12 Low Value | 416B | +13% | 0% |
| 30 | Mixtral 8x22B mixtral-8x22b |
Mistral | Open | $0.900 | $0.900 | 64K | 64 | 12 Low Value | 136B | -11% | 0% |
| 31 | Hunyuan-Turbo hunyuan-turbo |
Tencent | Flagship | $0.400 | $1.60 | 128K | 74 | 11 Low Value | 424B | +30% | 0% |
| 32 | Devstral Medium devstral-medium |
Mistral | Coding | $0.500 | $1.50 | 128K | 73 | 11 Low Value | 296B | +45% | 0% |
| 33 | Hy3 Preview hy3-preview |
Tencent | Flagship | $0.500 | $2.00 | 256K | 79 | 10 Low Value | 3.32T | 0% | 0% |
| 34 | MiMo V2.5 Pro mimo-v2-5-pro |
Xiaomi | Flagship | $0.500 | $2.00 | 128K | 78 | 10 Low Value | 749B | +33% | 0% |
| 35 | Hunyuan-T1 hunyuan-t1 |
Tencent | Reasoning | $0.500 | $2.00 | 128K | 77 | 9 Low Value | 285B | +71% | 0% |
| 36 | DeepSeek R1 deepseek-r1 |
DeepSeek | Reasoning | $0.550 | $2.19 | 64K | 79 | 9 Low Value | 248B | +3% | 0% |
| 37 | Owl Alpha owl-alpha |
OpenRouter | Reasoning | $0.600 | $2.40 | 200K | 76 | 8 Low Value | 2.01T | -24% | 0% |
| 38 | Kimi K2 Thinking kimi-k2-thinking |
Moonshot | Reasoning | $0.600 | $2.50 | 256K | 81 | 8 Low Value | 916B | +90% | 0% |
| 39 | Kimi Researcher kimi-researcher |
Moonshot | Reasoning | $0.600 | $2.50 | 256K | 76 | 8 Low Value | 188B | +105% | 0% |
| 40 | Claude Haiku 4.5 claude-haiku-4-5 |
Anthropic | Budget | $0.800 | $4.00 | 200K | 71 | 5 Low Value | 685B | +16% | 0% |
| 41 | Grok 4.6 grok-4-6 |
xAI | Reasoning | $2.00 | $6.00 | 2M | 88 | 3 Low Value | 1.40T | +117% | 0% |
| 42 | Magistral Medium 2 magistral-medium-2 |
Mistral | Reasoning | $2.00 | $5.00 | 128K | 73 | 3 Low Value | 464B | +80% | 0% |
| 43 | Pixtral Large pixtral-large |
Mistral | Flagship | $2.00 | $6.00 | 128K | 72 | 3 Low Value | 211B | +35% | 0% |
| 44 | Gemini 3.1 Pro gemini-3-1-pro |
Long-context | $2.50 | $10.00 | 2M | 86 | 2 Low Value | 1.27T | +28% | -5% | |
| 45 | Mistral Large 3 mistral-large-3 |
Mistral | Flagship | $3.00 | $9.00 | 128K | 78 | 2 Low Value | 386B | +6% | 0% |
| 46 | Grok 3 Reasoning grok-3-reasoning |
xAI | Reasoning | $2.00 | $10.00 | 128K | 75 | 2 Low Value | 294B | +9% | 0% |
| 47 | Claude Sonnet 4.6 claude-sonnet-4-6 |
Anthropic | Coding | $3.00 | $15.00 | 200K | 82 | 1 Low Value | 2.06T | +1% | 0% |
| 48 | GPT-5.6 gpt-5-6 |
OpenAI | Flagship | $6.00 | $36.00 | 400K | 91 | 1 Low Value | 1.72T | +34% | 0% |
| 49 | GPT-5.5 gpt-5-5 |
OpenAI | Flagship | $5.00 | $20.00 | 400K | 88 | 1 Low Value | 1.35T | +39% | -12% |
| 50 | Kimi K3 kimi-k3 |
Moonshot | Coding | $3.00 | $15.00 | 1M | 84 | 1 Low Value | 1.19T | +44% | 0% |
| 51 | Grok 4.1 grok-4.1 |
xAI | Long-context | $3.00 | $15.00 | 256K | 82 | 1 Low Value | 907B | +38% | 0% |
| 52 | Grok 4 Heavy grok-4-heavy |
xAI | Reasoning | $5.00 | $15.00 | 256K | 84 | 1 Low Value | 894B | +74% | 0% |
| 53 | GPT-5.4 gpt-5-4 |
OpenAI | Flagship | $5.00 | $20.00 | 400K | 85 | 1 Low Value | 811B | -26% | -10% |
| 54 | Grok 4 grok-4 |
xAI | Reasoning | $3.00 | $15.00 | 256K | 80 | 1 Low Value | 300B | +4% | 0% |
| 55 | Sonar Pro sonar-pro |
Perplexity | Long-context | $3.00 | $15.00 | 200K | 70 | 1 Low Value | 295B | +10% | 0% |
| 56 | Claude Fable 5 claude-fable-5 |
Anthropic | Flagship | $12.00 | $60.00 | 200K | 87 | 0 Low Value | 2.73T | +101% | -8% |
| 57 | GPT-6 Astra gpt-6-astra |
OpenAI | Flagship | $10.00 | $50.00 | 1.1M | 93 | 0 Low Value | 1.96T | +192% | 0% |
| 58 | Claude Opus 4.8 claude-opus-4-8 |
Anthropic | Flagship | $15.00 | $75.00 | 200K | 89 | 0 Low Value | 1.55T | +16% | 0% |
| 59 | Claude Opus 4.7 claude-opus-4-7 |
Anthropic | Flagship | $15.00 | $75.00 | 200K | 86 | 0 Low Value | 1.23T | +1% | 0% |
Token usage aggregated daily from Tokenscost calculator runs, public API mirrors, and OpenRouter ranking telemetry. Trailing 7-day window; figures refresh automatically each UTC day.