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 |
|---|---|---|---|---|---|---|---|---|
| 401 | Gemma 3 1BGoogle | — | 19.9 | — | — | — | Open | 12 Mar 2025 |
| 402 | Reka Flash 3Reka AI | — | — | — | 66K | $0.13 | Open | 12 Mar 2025 |
| 403 | computer-use-preview-2025-03-11 | — | — | — | — | — | — | 11 Mar 2025 |
| 404 | Skyfall 36B V2TheDrummer | — | — | — | 33K | $0.61 | Open | 10 Mar 2025 |
| 405 | Sonar Deep ResearchPerplexity | — | — | — | 128K | $3.50 | — | 7 Mar 2025 |
| 406 | Sonar ProPerplexity | — | — | — | 200K | $6.00 | — | 7 Mar 2025 |
| 407 | Sonar Reasoning ProPerplexity | — | — | — | 128K | $3.50 | — | 7 Mar 2025 |
| 408 | QwQ-32BAlibaba (Qwen) | 137.6 | 65.3 | — | — | — | Open | 5 Mar 2025 |
| 409 | GPT-4.5OpenAI | 136.7 | — | — | — | — | Closed | 27 Feb 2025 |
| 410 | GPT-4.5 Preview (Feb 2025)OpenAI | — | 68.7 | — | — | — | Closed | 27 Feb 2025 |
| 411 | Claude 3.7 SonnetAnthropic · +9 variants | 141.2 | 66.0 | — | — | — | Closed | 24 Feb 2025 |
| 412 | SabaMistral AI | — | — | — | 33K | $0.30 | — | 17 Feb 2025 |
| 413 | o3 Mini HighOpenAI | — | — | — | 200K | $1.93 | — | 12 Feb 2025 |
| 414 | Gemini 2.0 ProGoogle | 135.1 | — | — | — | — | Closed | 5 Feb 2025 |
| 415 | Gemini 2.0 Flash (Feb 2025)Google | 134.7 | 64.1 | — | — | — | Closed | 5 Feb 2025 |
| 416 | Gemini 2.0 Flash-LiteGoogle | — | — | — | — | — | Closed | 5 Feb 2025 |
| 417 | Gemini 2.0 Pro Exp (Feb 2025)Google | — | 65.7 | — | — | — | Closed | 5 Feb 2025 |
| 418 | Aion-RP 1.0 (8B)AionLabs | — | — | — | 33K | $1.00 | — | 4 Feb 2025 |
| 419 | Qwen-PlusAlibaba (Qwen) | — | — | — | 1M | $0.39 | — | 1 Feb 2025 |
| 420 | Qwen2.5 VL 72B InstructAlibaba (Qwen) | — | — | — | 128K | $0.85 | Open | 1 Feb 2025 |
| 421 | o3 MiniOpenAI · +1 variant | 140.3 | 77.0 | — | 200K | $1.93 | Closed | 31 Jan 2025 |
| 422 | o3-minimediumOpenAI | — | 74.3 | — | — | — | Closed | 31 Jan 2025 |
| 423 | Mistral Small 3Mistral AI | 127.1 | 47.3 | — | 33K | $0.058 | Open | 30 Jan 2025 |
| 424 | GPT-4o (Jan 2025)OpenAI | — | — | — | — | — | Closed | 29 Jan 2025 |
| 425 | SonarPerplexity | — | — | — | 127K | $1.00 | — | 27 Jan 2025 |
| 426 | Qwen2.5-MaxAlibaba (Qwen) | 132.5 | 56.1 | — | — | — | Closed | 25 Jan 2025 |
| 427 | Qwen Plus (Jan 2025)Alibaba (Qwen) | — | 48.1 | — | — | — | Closed | 25 Jan 2025 |
| 428 | Gemini 2.0 Flash Thinking (Jan 2025)Google | 135.4 | — | — | — | — | Closed | 21 Jan 2025 |
| 429 | Gemini 2.0 Flash Thinking ExpGoogle | — | 57.1 | — | — | — | Closed | 21 Jan 2025 |
| 430 | R1DeepSeek | 139.0 | 71.7 | — | 64K | $1.15 | Open | 20 Jan 2025 |
| 431 | DeepSeek-R1-Distill-Qwen-32BDeepSeek | 137.4 | 64.1 | — | — | — | Open | 20 Jan 2025 |
| 432 | DeepSeek-R1-Distill-Qwen-14BDeepSeek | 135.4 | 44.7 | — | — | — | Open | 20 Jan 2025 |
| 433 | DeepSeek-R1-Distill-Llama-70BDeepSeek | — | 55.7 | — | — | — | Open | 20 Jan 2025 |
| 434 | DeepSeek-R1-Distill-Qwen-1.5BDeepSeek | — | 33.6 | — | — | — | Open | 20 Jan 2025 |
| 435 | MiniMax-01MiniMax | — | — | — | 1M | $0.42 | Open | 15 Jan 2025 |
| 436 | CodestralMistral AI | — | — | — | — | — | Open | 13 Jan 2025 |
| 437 | Eurus-2-7B-PRIMETsinghua University,University of Illinois Urbana-Champaign (UIUC),Shanghai AI Lab,Peking University,Shanghai Jiao Tong University,CUHK Shenzhen Research Institute | — | 33.9 | — | — | — | Open | 31 Dec 2024 |
| 438 | DeepSeek V3DeepSeek | 132.4 | 56.5 | — | 164K | $0.45 | Open | 26 Dec 2024 |
| 439 | Llama 3.3 Euryale 70BSao10K | — | — | — | 131K | $0.68 | Open | 18 Dec 2024 |
| 440 | o1OpenAI · +3 variants | 141.9 | 76.8 | — | 200K | $26.25 | Closed | 17 Dec 2024 |
| 441 | Command R7B (12-2024)Cohere | — | — | — | 128K | $0.066 | — | 14 Dec 2024 |
| 442 | Grok-2 (Dec 2024)xAI | 130.5 | 53.8 | — | — | — | Closed | 12 Dec 2024 |
| 443 | Phi 4Microsoft | 130.4 | 56.1 | — | 16K | $0.087 | Open | 12 Dec 2024 |
| 444 | Gemini 2.0 Flash (Dec 2024)Google | 134.7 | — | — | — | — | Closed | 11 Dec 2024 |
| 445 | Llama 3.3 70BMeta | 127.3 | 47.4 | — | — | — | Open | 6 Dec 2024 |
| 446 | Llama 3.3 70B InstructMeta | — | — | — | 131K | $0.15 | Open | 6 Dec 2024 |
| 447 | Nova Lite 1.0Amazon | — | — | — | 300K | $0.10 | — | 5 Dec 2024 |
| 448 | Nova Micro 1.0Amazon | — | — | — | 128K | $0.061 | — | 5 Dec 2024 |
| 449 | Nova Pro 1.0Amazon | — | — | — | 300K | $1.40 | — | 5 Dec 2024 |
| 450 | Amazon Nova ProAmazon | 123.8 | — | — | — | — | Closed | 3 Dec 2024 |
— 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