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 |
|---|---|---|---|---|---|---|---|---|
| 601 | DeepSeek Coder 1.3BDeepSeek | 62.2 | — | — | — | — | Open | 2 Nov 2023 |
| 602 | llava-v1.5-7b | — | — | — | — | — | — | 5 Oct 2023 |
| 603 | Qwen-7BAlibaba (Qwen) | 106.5 | — | — | — | — | Open | 28 Sep 2023 |
| 604 | GPT-3.5 Turbo InstructOpenAI | — | — | — | 4K | $1.63 | — | 28 Sep 2023 |
| 605 | Mistral 7B v0.1Mistral AI | 112.0 | — | — | — | — | Open | 27 Sep 2023 |
| 606 | Qwen-14BAlibaba (Qwen) | 112.8 | — | — | — | — | Open | 24 Sep 2023 |
| 607 | Baichuan 2-7BBaichuan | 95.8 | — | — | — | — | Open | 20 Sep 2023 |
| 608 | internlm-20b | 111.8 | — | — | — | — | Closed | 18 Sep 2023 |
| 609 | internlm-chat-20b | — | — | — | — | — | — | 17 Sep 2023 |
| 610 | Phi-1.5Microsoft | 90.8 | — | — | — | — | Open | 11 Sep 2023 |
| 611 | Falcon-180BTechnology Innovation Institute | 111.9 | — | — | — | — | Open | 6 Sep 2023 |
| 612 | Baichuan2-13BBaichuan | 102.8 | — | — | — | — | Open | 6 Sep 2023 |
| 613 | Baichuan2-13B-Chat | — | — | — | — | — | — | 6 Sep 2023 |
| 614 | GPT-3.5 Turbo 16kOpenAI | — | — | — | 16K | $3.25 | — | 28 Aug 2023 |
| 615 | Qwen-VL-Chat | — | — | — | — | — | — | 20 Aug 2023 |
| 616 | Claude InstantAnthropic | 120.2 | — | — | — | — | Closed | 9 Aug 2023 |
| 617 | Weaver (alpha)Mancer | — | — | — | 8K | $0.49 | — | 2 Aug 2023 |
| 618 | ReMM SLERP 13Bundi95 | — | — | — | 6K | $0.42 | Open | 22 Jul 2023 |
| 619 | Stable Beluga 2Stability AI | 117.0 | — | — | — | — | Open | 20 Jul 2023 |
| 620 | Llama 2-70BMeta | 113.6 | 26.3 | — | — | — | Open | 18 Jul 2023 |
| 621 | Llama 2-13BMeta | 105.8 | — | — | — | — | Open | 18 Jul 2023 |
| 622 | Llama 2-34BMeta | 104.8 | — | — | — | — | Closed | 18 Jul 2023 |
| 623 | Llama 2-7BMeta | 98.5 | — | — | — | — | Open | 18 Jul 2023 |
| 624 | Claude 2Anthropic | 120.1 | 34.7 | — | — | — | Closed | 11 Jul 2023 |
| 625 | Baichuan 1-13BBaichuan | — | — | — | — | — | Open | 11 Jul 2023 |
| 626 | internlm-7b | 102.4 | — | — | — | — | Closed | 5 Jul 2023 |
| 627 | MythoMax 13Bgryphe | — | — | — | 8K | $0.087 | Open | 2 Jul 2023 |
| 628 | XGen-7BSalesforce | 92.8 | — | — | — | — | Open | 27 Jun 2023 |
| 629 | chatglm2-6b | 98.4 | — | — | — | — | Closed | 24 Jun 2023 |
| 630 | MPT-30BMosaicML | 100.2 | — | — | — | — | Open | 22 Jun 2023 |
| 631 | Inflection-1Inflection AI | — | — | — | — | — | Closed | 22 Jun 2023 |
| 632 | Vicuna-13B-v1.3Large Model Systems Organization,University of California (UC) Berkeley | — | — | — | — | — | Open | 18 Jun 2023 |
| 633 | GPT-4 (Jun 2023)OpenAI | 123.1 | 30.7 | — | — | — | Closed | 13 Jun 2023 |
| 634 | GPT-3.5 Turbo (Jun 2023)OpenAI | 113.1 | — | — | — | — | Closed | 13 Jun 2023 |
| 635 | GPT-3.5 Turbo (June 2023)OpenAI | — | — | — | — | — | Closed | 13 Jun 2023 |
| 636 | open_llama_7b | 91.0 | — | — | — | — | Closed | 7 Jun 2023 |
| 637 | Baichuan1-7BBaichuan | 89.8 | — | — | — | — | Open | 1 Jun 2023 |
| 638 | GPT-3.5 TurboOpenAI · +1 variant | — | — | — | 16K | $0.75 | — | 28 May 2023 |
| 639 | GPT-4OpenAI | — | — | — | 8K | $37.50 | — | 28 May 2023 |
| 640 | Falcon-40BTechnology Innovation Institute | 104.0 | — | — | — | — | Open | 25 May 2023 |
| 641 | instructblip-vicuna-7b | — | — | — | — | — | — | 22 May 2023 |
| 642 | PaLM 2-L | 114.8 | — | — | — | — | Closed | 17 May 2023 |
| 643 | PaLM 2-M | 108.0 | — | — | — | — | Closed | 17 May 2023 |
| 644 | PaLM 2-S | 105.8 | — | — | — | — | Closed | 17 May 2023 |
| 645 | MPT-7BMosaicML | 94.0 | — | — | — | — | Open | 5 May 2023 |
| 646 | RedPajama-INCITE-7B-Base | 89.7 | — | — | — | — | Closed | 4 May 2023 |
| 647 | Falcon-7BTechnology Innovation Institute | 94.5 | — | — | — | — | Open | 24 Apr 2023 |
| 648 | stablelm-tuned-alpha-7b | 54.3 | — | — | — | — | Closed | 19 Apr 2023 |
| 649 | Claude 1.3Anthropic | — | — | — | — | — | Closed | 18 Apr 2023 |
| 650 | vicuna-13b-v1.1 | 94.0 | — | — | — | — | Closed | 12 Apr 2023 |
— 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