Newest models
Most recent releases, with whatever independent scores exist so far.
Most recent releases, with whatever independent scores exist so far. Source: OpenRouter / Epoch AI. Variants (reasoning effort, batch) are folded into one row.
| # | Model | Capability | Reasoning | Coding | Context | $/M | Weights | Released |
|---|---|---|---|---|---|---|---|---|
| 251 | Nova Premier 1.0Amazon | — | — | — | 1M | $5.00 | — | 31 Oct 2025 |
| 252 | Sonar Pro SearchPerplexity | — | — | — | 200K | $6.00 | — | 30 Oct 2025 |
| 253 | Voxtral Small 24B 2507Mistral AI | — | — | — | 33K | $0.15 | Open | 30 Oct 2025 |
| 254 | gpt-oss-safeguard-20bOpenAI | — | — | — | 131K | $0.13 | Open | 29 Oct 2025 |
| 255 | granite-4.0-1b | — | 24.0 | — | — | — | — | 28 Oct 2025 |
| 256 | granite-4.0-350m | — | 11.2 | — | — | — | — | 28 Oct 2025 |
| 257 | MiniMax M2MiniMax | — | — | — | 205K | $0.53 | Open | 23 Oct 2025 |
| 258 | Qwen3 VL 32B InstructAlibaba (Qwen) | — | — | — | 131K | $0.18 | Open | 23 Oct 2025 |
| 259 | Granite 4.0 MicroIBM | — | 28.3 | — | 131K | $0.041 | Open | 20 Oct 2025 |
| 260 | GPT-5 Image MiniOpenAI | — | — | — | 400K | $2.38 | — | 16 Oct 2025 |
| 261 | Claude Haiku 4.5Anthropic · +3 variants | 142.4 | 71.2 | — | 200K | $2.00 | Closed | 15 Oct 2025 |
| 262 | GPT-5 ImageOpenAI | — | — | — | 400K | $10.00 | — | 14 Oct 2025 |
| 263 | Qwen3 VL 8B InstructAlibaba (Qwen) | — | — | — | 262K | $0.20 | Open | 14 Oct 2025 |
| 264 | Qwen3 VL 8B ThinkingAlibaba (Qwen) | — | — | — | 131K | $0.66 | Open | 14 Oct 2025 |
| 265 | GPT-5 ProOpenAI · +1 variant | 150.3 | — | — | 400K | $41.25 | Closed | 7 Oct 2025 |
| 266 | Nano Banana (Gemini 2.5 Flash Image)Google | — | — | — | 33K | $0.85 | — | 7 Oct 2025 |
| 267 | Qwen3 VL 30B A3B InstructAlibaba (Qwen) | — | — | — | 262K | $0.26 | Open | 6 Oct 2025 |
| 268 | Qwen3 VL 30B A3B ThinkingAlibaba (Qwen) | — | — | — | 262K | $0.75 | Open | 6 Oct 2025 |
| 269 | tiny-recursion-model | — | — | — | — | — | — | 6 Oct 2025 |
| 270 | GLM 4.6Z.ai (Zhipu AI) | — | — | — | 205K | $0.76 | Open | 30 Sep 2025 |
| 271 | GLM-4.6 (Together)Z.ai (Zhipu AI) | — | — | — | — | — | Open | 30 Sep 2025 |
| 272 | Claude Sonnet 4.5Anthropic · +12 variants | 146.8 | — | — | 1M | $6.00 | Closed | 29 Sep 2025 |
| 273 | DeepSeek V3.2 ExpDeepSeek | 145.0 | — | — | 164K | $0.30 | Open | 29 Sep 2025 |
| 274 | Cydonia 24B V4.1TheDrummer | — | — | — | 131K | $0.35 | Open | 27 Sep 2025 |
| 275 | gemini-robotics-er-1.5-preview | — | — | — | — | — | — | 26 Sep 2025 |
| 276 | Relace Apply 3Relace | — | — | — | 256K | $0.95 | — | 26 Sep 2025 |
| 277 | Gemini 2.5 Flash (Sep 2025)Google | 143.0 | — | — | — | — | Closed | 25 Sep 2025 |
| 278 | Gemini 2.5 Flash-Lite (Sep 2025)Google | — | — | — | — | — | Closed | 25 Sep 2025 |
| 279 | Qwen3 MaxAlibaba (Qwen) | 142.4 | — | — | 262K | $1.56 | Closed | 24 Sep 2025 |
| 280 | Qwen3-Max-InstructAlibaba (Qwen) | — | 72.6 | — | — | — | Closed | 24 Sep 2025 |
| 281 | Qwen3 Coder PlusAlibaba (Qwen) | — | — | — | 1M | $1.30 | — | 23 Sep 2025 |
| 282 | Qwen3 VL 235B A22B InstructAlibaba (Qwen) | — | — | — | 262K | $0.63 | Open | 23 Sep 2025 |
| 283 | Qwen3 VL 235B A22B ThinkingAlibaba (Qwen) | — | — | — | 131K | $1.30 | Open | 23 Sep 2025 |
| 284 | DeepSeek V3.1 TerminusDeepSeek | — | — | — | 164K | $0.47 | Open | 22 Sep 2025 |
| 285 | Grok 4 FastxAI | 144.2 | — | — | — | — | Closed | 19 Sep 2025 |
| 286 | Magistral Small 1.2Mistral AI | 131.4 | 47.6 | — | — | — | Open | 18 Sep 2025 |
| 287 | Qwen3 Coder FlashAlibaba (Qwen) | — | — | — | 1M | $0.39 | — | 17 Sep 2025 |
| 288 | GPT-5-codexOpenAI | — | — | — | — | — | Closed | 15 Sep 2025 |
| 289 | Qwen3 Next 80B A3B InstructAlibaba (Qwen) | — | — | — | 262K | $0.35 | Open | 11 Sep 2025 |
| 290 | Qwen3 Next 80B A3B ThinkingAlibaba (Qwen) | — | — | — | 262K | $0.41 | Open | 11 Sep 2025 |
| 291 | Qwen Plus 0728Alibaba (Qwen) | — | — | — | 1M | $0.39 | — | 8 Sep 2025 |
| 292 | Kimi K2 (Sep 2025)Moonshot AI | — | — | — | — | — | Open | 5 Sep 2025 |
| 293 | Kimi K2 0905 (Novita)Moonshot AI | — | — | — | — | — | Open | 5 Sep 2025 |
| 294 | Kimi K2 Instruct (0905)Moonshot AI | — | — | — | — | — | Open | 5 Sep 2025 |
| 295 | Kimi K2 0905Moonshot AI | — | — | — | 262K | $1.07 | Open | 4 Sep 2025 |
| 296 | grok-code-fast-1xAI | — | — | — | — | — | — | 28 Aug 2025 |
| 297 | Qwen3 30B A3B Thinking 2507Alibaba (Qwen) | — | — | — | 82K | $0.75 | Open | 28 Aug 2025 |
| 298 | Hermes 4 405BNous Research | — | — | — | 131K | $1.50 | Open | 26 Aug 2025 |
| 299 | DeepSeek V3.1DeepSeek | 139.9 | — | — | 164K | $0.42 | Open | 21 Aug 2025 |
| 300 | seed-oss-36b-instruct | — | 71.5 | — | — | — | — | 20 Aug 2025 |
— means no published score from that source yet · click a model for every benchmark with its source
Best AI for coding →
Models ranked on DeepSWE
Best AI for reasoning →
Ranked on GPQA Diamond
Best AI for math →
Ranked on competition math
Best open-weight models →
Weights you can run yourself
Cheapest capable models →
Lowest blended API price
Best AI coding tools →
Apps & agents by popularity
Best AI image generators →
Apps & models
Best AI for research →
Answer engines & deep research