LLM models for structured extraction

Name: Entity Enricher LLM model catalog
Creator: Entity Enricher

Every model of the catalog with its vendor pricing, measured capabilities and the scores it earned on our public benchmark scenarios. The table reads one static file, the same one you can download.

Updated Oct 10, 2026, 7:25 AM UTC2551 models · 144 providers4 public benchmark scenarios

Download models.json

1.1 MBField reference

Task

Scores come from the scenarios published for this task. Speed and cost are relative to the other models on the same scenario.

Overall score blendQuality 34 · Speed 33 · Cost 33

Quality34 %Speed33 %Cost33 %

Benchmarked only

Enrichment-capable only224 of 2551 models

Capabilities

Blend: Quality 34 · Speed 33 · Cost 33224 models


Voxtral Small (latest)mistral-ai::voxtral-small-latest	80	74	80	88	0.10	0.40	33k	—
Gemini 3.1 Flash Lite (preview)Retires May 25, 2026google::gemini-3.1-flash-lite-preview	78	81	86	69	0.25	1.50	1M	15.6
Voxtral Small (2507)Retires May 30, 2026mistral-ai::voxtral-small-2507	78	71	80	82	0.10	0.40	33k	—
Gemini 3.1 Flash LiteRetires May 7, 2027google::gemini-3.1-flash-lite	78	80	86	67	0.25	1.50	1M	—
DeepSeek Coderdeepseek::deepseek-coder	77	80	73	79	0.14	0.28	128k	—
DeepSeek ReasonerRetires Jul 24, 2026deepseek::deepseek-reasoner	76	78	73	78	0.28	0.42	131k	13.1
Gemini 3.5 Flash Litegoogle::gemini-3.5-flash-lite	74	80	84	58	0.30	2.50	1M	22.2
DeepSeek ChatRetires Jul 24, 2026deepseek::deepseek-chat	74	79	74	69	0.28	0.42	131k	—
Gemini Flash Lite (latest)google::gemini-flash-lite-latest	74	80	83	58	0.30	2.50	1M	—
DeepSeek V4 Flashdeepseek::deepseek-v4-flash	73	82	72	66	0.30	1.20	1M	18.9
Mistral Code (latest)mistral-ai::mistral-code-latest	73	66	76	79	0.30	0.90	128k	—
Qwen3 30B A3B Instruct (2507)alibaba::qwen3-30b-a3b-instruct-2507	73	64	70	86	0.05	0.19	262k	7.5
DeepSeek Flashdeepseek::deepseek-flash	73	80	74	64	0.30	1.20	1M	—
Mistral Vibe Cli Fastmistral-ai::mistral-vibe-cli-fast	72	70	71	77	0.15	0.60	262k	—
Labs Leanstral 1.5.1Retires Sep 30, 2026mistral-ai::labs-leanstral-1-5-1	72	61	56	100	0.00	0.00	262k	—
Qwen3.5 Flashalibaba::qwen3.5-flash	72	73	65	78	0.07	0.26	1M	—
GPT 4.1 Miniopenai::gpt-4.1-mini	72	78	75	61	0.40	1.60	1M	10.2
Mistral Small (2603)mistral-ai::mistral-small-2603	72	71	71	73	0.15	0.60	262k	5.8
Grok 4 Fast ReasoningRetires May 15, 2026xai::grok-4-fast-reasoning	71	71	60	81	0.20	0.50	2M	—
DeepSeek V4 Flash Vision (exp)deepseek::deepseek-v4-flash-vision-exp	71	82	67	62	0.30	1.20	1M	34.8
GPT 4.1 NanoRetires Oct 23, 2026openai::gpt-4.1-nano	71	68	72	72	0.10	0.40	1M	7.8
Mistral Code Fim (latest)mistral-ai::mistral-code-fim-latest	70	67	76	68	0.30	0.90	128k	—
Gemini 2.5 Flash Litegoogle::gemini-2.5-flash-lite	70	32	91	88	0.10	0.40	1M	6.7
Grok 4.1 Fast ReasoningRetires May 15, 2026xai::grok-4-1-fast-reasoning	70	68	61	81	0.20	0.50	2M	—
Ministral 14B (2512)mistral-ai::ministral-14b-2512	70	73	65	72	0.20	0.20	262k	6.0
GPT 4o Miniopenai::gpt-4o-mini	70	68	68	73	0.15	0.60	128k	6.7
Pixtral 12Bmistral-ai::pixtral-12b	70	71	63	76	0.15	0.15	128k	—
Ministral 3B (latest)mistral-ai::ministral-3b-latest	70	20	90	100	0.10	0.10	131k	—
Claude Haiku 5.5anthropic::claude-haiku-5-5	70	74	69	66	0.10	0.50	1M	—
GPT 6 Lunaopenai::gpt-6-luna	69	82	57	68	0.10	0.50	922k	18.5
Open Mistral Nemo (2407)Retires Jul 31, 2026mistral-ai::open-mistral-nemo-2407	69	70	67	71	0.30	0.30	128k	—
Ministral 14B (latest)mistral-ai::ministral-14b-latest	69	71	63	74	0.20	0.20	262k	—
Qwen3 Coder 30B A3B Instructalibaba::qwen3-coder-30b-a3b-instruct	69	66	63	78	0.07	0.26	160k	9.6
Grok 4 Fast Non ReasoningRetires May 15, 2026xai::grok-4-fast-non-reasoning	69	81	68	59	0.20	0.50	2M	—
Ministral 3B (2512)mistral-ai::ministral-3b-2512	69	29	88	90	0.10	0.10	131k	4.8
Grok 4.20 Non Reasoning (latest)xai::grok-4.20-non-reasoning-latest	69	80	68	58	1.25	2.50	1M	—
Grok 4.20 Beta 0309 Non Reasoningxai::grok-4.20-beta-0309-non-reasoning	68	80	66	58	1.25	2.50	1M	—
Grok 4.20 Non Reasoningxai::grok-4.20-non-reasoning	68	80	67	56	1.25	2.50	1M	—
Grok 4.20 Experimental Beta Non Reasoning (latest)xai::grok-4.20-experimental-beta-non-reasoning-latest	68	80	67	56	1.25	2.50	1M	—
Gemini Flash (latest)google::gemini-flash-latest	68	84	73	46	0.75	3.75	1M	—
Gemini 3.8 Flashgoogle::gemini-3.8-flash	68	85	72	45	0.75	3.75	1M	40.9
Grok 4.20 Beta Non Reasoningxai::grok-4.20-beta-non-reasoning	67	80	66	55	1.25	2.50	1M	—
Qwen3.5 35B A3Balibaba::qwen3.5-35b-a3b	67	69	65	68	0.08	0.75	262k	15.1
Gemini 3.7 Flashgoogle::gemini-3.7-flash	67	85	73	44	0.75	3.75	1M	39.1
GPT 5.4 Miniopenai::gpt-5.4-mini	67	76	77	48	0.75	4.50	272k	11.1
Codestral (2508)mistral-ai::codestral-2508	67	66	74	61	0.30	0.90	256k	—
Qwen3 Coder Flashalibaba::qwen3-coder-flash	67	68	64	69	0.20	0.98	998k	—
Grok 4.20 Non Reasoning Gv2xai::grok-4.20-non-reasoning-gv2	67	80	65	55	1.25	2.50	1M	—
Grok 4.1 Fast Non Reasoning (latest)Retires May 15, 2026xai::grok-4-1-fast-non-reasoning-latest	66	78	66	54	1.25	2.50	2M	—
Grok 4.20 0309 Non Reasoningxai::grok-4.20-0309-non-reasoning	66	80	64	53	1.25	2.50	1M	—
Grok 3 MiniRetires Feb 28, 2026xai::grok-3-mini	66	67	57	74	0.25	0.50	131k	14.6
Grok 4.20 Experimental Beta 0304 Non Reasoningxai::grok-4.20-experimental-beta-0304-non-reasoning	66	78	65	54	1.25	2.50	1M	—
Grok 3 Fast (latest)Retires May 15, 2026xai::grok-3-fast-latest	66	70	63	63	1.25	2.50	131k	—
Grok 3 Mini (latest)Retires Feb 28, 2026xai::grok-3-mini-latest	66	67	66	64	1.25	2.50	131k	—
Qwen3.5 122B A10Balibaba::qwen3.5-122b-a10b	65	73	63	60	0.26	0.90	262k	15.6
Grok 3 Mini FastRetires Feb 28, 2026xai::grok-3-mini-fast	65	68	64	63	1.25	2.50	131k	—
DeepSeek V4 Flashalibaba::deepseek-v4-flash	65	80	50	65	0.20	0.40	1M	18.9
GLM 4 32B 0414 128kzai::glm-4-32b-0414-128k	65	68	52	75	0.10	0.10	128k	—
Grok 4.1 Fast Non ReasoningRetires May 15, 2026xai::grok-4-1-fast-non-reasoning	65	80	64	51	0.00	0.00	2M	—
Grok 4Retires May 15, 2026xai::grok-4	65	72	64	59	3.00	15.00	256k	22.5
Qwen Plus (2025-01-25)alibaba::qwen-plus-2025-01-25	65	74	60	60	0.40	1.20	129k	—
Grok 3 Mini Fast (latest)Retires Feb 28, 2026xai::grok-3-mini-fast-latest	65	66	65	63	1.25	2.50	131k	—
Grok 3 Mini Fast (beta)Retires Feb 28, 2026xai::grok-3-mini-fast-beta	65	67	65	61	1.25	2.50	131k	—
Grok 4 (latest)Retires May 15, 2026xai::grok-4-latest	65	69	62	63	1.25	2.50	256k	—
Command A Plus (05-2026)cohere::command-a-plus-05-2026	64	80	13	100	0.00	0.00	128k	—
Grok 4.20 Beta Latest Non Reasoningxai::grok-4.20-beta-latest-non-reasoning	64	81	66	46	1.25	2.50	1M	—
Grok 4.3xai::grok-4.3	64	67	61	64	1.25	2.50	1M	14.0
Qwen3.7 Flashalibaba::qwen3.7-flash	64	73	40	80	0.03	0.13	1M	—
Grok 4.3 (latest)xai::grok-4.3-latest	64	67	62	62	1.25	2.50	1M	—
Qwen3 30B A3Balibaba::qwen3-30b-a3b	64	60	62	71	0.12	0.50	129k	6.6
Grok 3 Mini (beta)Retires Feb 28, 2026xai::grok-3-mini-beta	64	66	63	63	0.30	0.50	131k	—
Grok 4.1 Fast Reasoning (latest)Retires May 15, 2026xai::grok-4-1-fast-reasoning-latest	63	68	62	59	1.25	2.50	2M	—
GPT 4.1openai::gpt-4.1	63	82	73	34	2.00	8.00	1M	12.7
Grok 4.1 FastRetires May 15, 2026xai::grok-4-1-fast	63	67	64	57	1.25	2.50	2M	11.3
Grok 3 (beta)Retires May 15, 2026xai::grok-3-beta	63	69	63	56	3.00	15.00	131k	—
GPT 4oopenai::gpt-4o	62	75	74	37	2.50	10.00	128k	—
Grok 3 (latest)Retires May 15, 2026xai::grok-3-latest	62	68	55	64	1.25	2.50	131k	—
Grok 3 Fast (beta)Retires May 15, 2026xai::grok-3-fast-beta	62	63	57	65	1.25	2.50	131k	—
Qwen3.5 27Balibaba::qwen3.5-27b	62	69	54	62	0.20	0.90	262k	19.4
Grok 4.20 Reasoningxai::grok-4.20-reasoning	62	78	46	61	1.25	2.50	1M	—
GLM 5.2together-ai::zai-org/GLM-5.2	62	66	72	46	1.40	4.40	1M	—
GLM 4.6v Flashxzai::glm-4.6v-flashx	61	62	47	75	0.04	0.40	128k	—
Gemini Robotics Er 2 (preview)google::gemini-robotics-er-2-preview	61	83	64	36	1.00	5.00	131k	—
Gemini 2.5 Flashgoogle::gemini-2.5-flash	61	81	58	43	0.30	2.50	1M	8.7
Mistral Medium 3.5mistral-ai::mistral-medium-3-5	61	75	70	37	1.50	7.50	262k	14.2
Grok 4.20 (experimental, beta, latest)xai::grok-4.20-experimental-beta-latest	61	81	44	57	1.25	2.50	1M	—
GLM 4.6vzai::glm-4.6v	61	65	53	63	0.30	0.90	128k	—
Grok 4.20 (experimental, beta, 0304)xai::grok-4.20-experimental-beta-0304	61	80	45	57	1.25	2.50	1M	—
Gemini 3 Flash (preview)google::gemini-3-flash-preview	61	83	59	39	0.50	3.00	1M	17.9
GPT 5.4openai::gpt-5.4	60	82	66	33	2.50	15.00	1.1M	18.2
Qwen3.5 397B A17Balibaba::qwen3.5-397b-a17b	60	76	47	57	0.39	0.90	262k	18.4
Gemini 3.6 Flashgoogle::gemini-3.6-flash	60	82	59	38	0.75	3.75	1M	34.0
Grok 4.20 Beta Latest Reasoningxai::grok-4.20-beta-latest-reasoning	60	79	43	57	1.25	2.50	1M	—
Qwen3 235B A22Balibaba::qwen3-235b-a22b	60	72	51	56	0.46	0.90	131k	12.0
Grok 4.20 Reasoning Gv2xai::grok-4.20-reasoning-gv2	60	77	45	56	1.25	2.50	1M	—
GPT 5.1Retires Apr 1, 2027openai::gpt-5.1	59	76	69	33	1.50	12.00	272k	13.3
Grok 4.20 (beta)xai::grok-4.20-beta	59	77	43	57	1.25	2.50	1M	—
Grok 4.20 Beta Reasoningxai::grok-4.20-beta-reasoning	59	81	44	51	1.25	2.50	1M	—
Qwen3.6 27Balibaba::qwen3.6-27b	59	73	47	57	0.30	0.90	262k	19.8
Grok 4.20 Experimental Beta Reasoning (latest)xai::grok-4.20-experimental-beta-reasoning-latest	59	78	42	55	1.25	2.50	1M	—
Qwen3.5 Plusalibaba::qwen3.5-plus	59	77	45	54	0.26	1.56	992k	—
GPT 5 Nanoopenai::gpt-5-nano	59	68	46	62	0.05	0.40	272k	7.1
GPT OSS Safeguard 20Bgroq::openai/gpt-oss-safeguard-20b	59	69	37	70	0.08	0.30	131k	—
DeepSeek V4.1 Flashtogether-ai::deepseek-ai/DeepSeek-V4.1-Flash	59	80	43	52	0.30	1.20	1M	24.7
Grok 4.20 0309 Reasoningxai::grok-4.20-0309-reasoning	58	74	42	59	1.25	2.50	1M	—
GPT 5.4 NanoRetires Apr 1, 2027openai::gpt-5.4-nano	58	57	62	56	0.20	1.25	272k	11.7
GLM 4.7 Flashzai::glm-4.7-flash	58	46	29	100	0.00	0.00	200k	—
Qwen Maxalibaba::qwen-max	58	74	61	39	1.60	6.40	31k	8.0
Mistral Medium (2312)Retires Jun 16, 2025mistral-ai::mistral-medium-2312	58	74	68	32	2.70	8.10	32k	—
Grok 4.20 (beta, latest)xai::grok-4.20-beta-latest	58	80	43	51	1.25	2.50	1M	—
Grok 4.20 Experimental Beta 0304 Reasoningxai::grok-4.20-experimental-beta-0304-reasoning	58	71	44	58	1.25	2.50	1M	—
Qwen3.6 Flashalibaba::qwen3.6-flash	58	71	50	53	0.19	1.13	1M	—
Mistral Medium 3mistral-ai::mistral-medium-3	58	75	65	34	1.50	7.50	262k	9.0
Ternary Bonsai 27Btogether-ai::Prism-ML/Ternary-Bonsai-27B	58	31	44	100	0.00	0.00	262k	—
Claude Sonnet 5Retires Jun 30, 2027anthropic::claude-sonnet-5	58	85	60	28	2.00	10.00	1M	23.2
DeepSeek V4 Pro (0813)together-ai::deepseek-ai/DeepSeek-V4-Pro-0813	58	17	98	60	1.32	3.96	1M	20.4
Qwen3.5 9Btogether-ai::Qwen/Qwen3.5-9B	58	47	51	75	0.17	0.25	262k	11.2
Grok 4.20 Reasoning (latest)xai::grok-4.20-reasoning-latest	57	66	44	63	1.25	2.50	1M	—
Claude Haiku 4.5Retires Oct 15, 2026anthropic::claude-haiku-4-5	57	67	65	40	1.00	5.00	200k	15.4
Grok 4.20xai::grok-4.20	57	77	39	55	1.25	2.50	1M	—
GPT 5.2openai::gpt-5.2	57	71	65	36	1.75	14.00	272k	17.0
O3 MiniRetires Oct 23, 2026openai::o3-mini	57	74	60	36	1.10	4.40	200k	12.5
Qwen3 Coder Plusalibaba::qwen3-coder-plus	57	59	60	53	0.65	3.25	998k	—
GLM 4.5vzai::glm-4.5v	57	77	42	51	0.60	1.80	66k	—
Qwen3 VL 30B A3B Thinkingalibaba::qwen3-vl-30b-a3b-thinking	57	71	45	53	0.20	0.90	131k	—
Grok 4.20 Beta 0309 Reasoningxai::grok-4.20-beta-0309-reasoning	57	75	43	52	1.25	2.50	1M	—
Mistral Code Agent (latest)mistral-ai::mistral-code-agent-latest	57	76	52	42	0.40	2.00	256k	—
Mistral Vibe Cli With Toolsmistral-ai::mistral-vibe-cli-with-tools	57	75	62	32	1.50	7.50	262k	—
Gemini 3.5 Flashgoogle::gemini-3.5-flash	57	83	60	26	1.50	9.00	1M	23.8
DeepSeek V4 Prodeepseek::deepseek-v4-pro	56	55	65	50	1.32	3.96	1M	20.4
Mistral Vibe Cli (latest)mistral-ai::mistral-vibe-cli-latest	56	75	61	33	1.50	7.50	262k	—
O3openai::o3	56	80	57	31	2.00	8.00	200k	20.2
O4 MiniRetires Oct 23, 2026openai::o4-mini	56	78	50	39	1.10	4.40	200k	16.7
Chat (latest)openai::chat-latest	56	77	67	22	5.00	30.00	400k	—
GLM 5v Turbozai::glm-5v-turbo	56	78	44	44	1.20	4.00	200k	—
Grok 3Retires May 15, 2026xai::grok-3	55	67	50	49	3.00	15.00	131k	10.4
Grok 3 Fastxai::grok-3-fast	55	71	57	37	5.00	25.00	131k	—
Grok Code Fast 1Retires May 15, 2026xai::grok-code-fast-1	55	79	28	58	1.00	2.00	256k	14.1
Grok Code FastRetires May 15, 2026xai::grok-code-fast	55	75	30	59	1.00	2.00	256k	—
GLM 4.5 Airzai::glm-4.5-air	55	18	72	75	0.20	1.10	128k	—
GLM 4.5 FlashRetires Jan 30, 2026zai::glm-4.5-flash	55	18	46	100	0.00	0.00	200k	—
Grok 4.5xai::grok-4.5	55	82	41	40	2.00	6.00	500k	38.8
GPT 5 Miniopenai::gpt-5-mini	54	69	46	47	0.25	2.00	272k	9.9
GPT 6.1 Solopenai::gpt-6.1-sol	54	79	48	34	2.00	10.00	922k	—
Inklingtogether-ai::thinkingmachines/Inkling	54	81	49	32	1.00	4.05	524k	25.0
Grok Build 0.1xai::grok-build-0.1	54	79	29	52	1.00	2.00	256k	—
GPT 3.5 TurboRetires Oct 23, 2026openai::gpt-3.5-turbo	54	13	90	59	0.50	1.50	16k	5.5
Muse Glimmer 30Btogether-ai::meta-models/Muse-Glimmer-30B	54	72	41	47	0.35	1.50	131k	—
Gemini 2.5 Progoogle::gemini-2.5-pro	53	80	53	26	1.25	10.00	1M	16.1
Qwen3.7 Plusalibaba::qwen3.7-plus	53	83	31	45	0.32	1.28	992k	25.2
GPT 6 Solopenai::gpt-6-sol	53	79	51	28	2.00	10.00	922k	28.5
Mistral Large (2407)Retires Mar 30, 2025mistral-ai::mistral-large-2407	53	77	51	30	2.00	6.00	131k	7.6
Grok 4.5 (latest)xai::grok-4.5-latest	53	80	39	39	2.00	6.00	500k	—
GPT 5.6 Terraopenai::gpt-5.6-terra	53	82	48	28	2.00	12.00	922k	20.8
Claude Opus 4.5Retires Nov 24, 2026anthropic::claude-opus-4-5	53	85	55	16	5.00	25.00	200k	23.7
Gemini 3.1 Pro Preview Customtoolsgoogle::gemini-3.1-pro-preview-customtools	52	83	52	21	2.00	12.00	1M	—
Claude Sonnet 4.6Retires Feb 17, 2027anthropic::claude-sonnet-4-6	52	80	51	23	3.00	15.00	1M	23.3
GLM 4.5 Airxzai::glm-4.5-airx	52	23	74	59	1.10	4.50	128k	—
Gemini Pro (latest)google::gemini-pro-latest	51	83	50	20	2.00	12.00	1M	—
Qwen3.8 Flashalibaba::qwen3.8-flash	51	76	20	56	0.15	0.47	992k	—
Grok Build (latest)xai::grok-build-latest	51	78	35	38	2.00	6.00	500k	—
Claude Sonnet 4.5Retires Nov 30, 2026anthropic::claude-sonnet-4-5	51	78	51	22	3.00	15.00	200k	19.3
Claude Opus 4.6Retires Feb 5, 2027anthropic::claude-opus-4-6	51	84	51	16	5.00	25.00	1M	26.4
Qwen3.8 27Bgroq::qwen/qwen3.8-27b	51	66	42	43	0.80	4.00	131k	20.2
Kimi K2.7 Code Highspeedmoonshotai::kimi-k2.7-code-highspeed	50	82	48	20	1.90	8.00	262k	—
GLM 4.7zai::glm-4.7	50	74	29	46	0.60	2.20	200k	—
Qwen3.7 Maxalibaba::qwen3.7-max	50	80	44	25	2.50	7.50	992k	29.5
Qwen3 VL 235B A22B Thinkingalibaba::qwen3-vl-235b-a22b-thinking	50	77	37	36	0.40	4.00	131k	—
GPT OSS 120Bgroq::openai/gpt-oss-120b	50	46	44	60	0.15	0.60	131k	10.2
Claude Opus 5Retires Jul 24, 2027anthropic::claude-opus-5	49	86	49	11	5.00	25.00	1M	50.8
GLM 5.3together-ai::zai-org/GLM-5.3	49	25	77	46	1.40	4.40	1M	—
GLM 4.6zai::glm-4.6	49	76	27	43	0.60	2.20	200k	—
Qwen3 Maxalibaba::qwen3-max	49	76	31	39	0.78	3.90	258k	12.6
GLM 4.5zai::glm-4.5	49	76	27	42	0.60	2.20	128k	—
Qwen3.8 2.4t A95Btogether-ai::Qwen/Qwen3.8-2.4T-A95B	49	63	42	40	2.00	6.00	1M	39.9
Gemini 3.1 Pro (preview)google::gemini-3.1-pro-preview	48	83	42	19	2.00	12.00	1M	29.7
Qwen3.6 Max (preview)alibaba::qwen3.6-max-preview	48	83	35	26	1.03	6.16	262k	—
GPT 5.6openai::gpt-5.6	48	83	42	18	4.00	20.00	922k	—
GLM 4.6v Flashzai::glm-4.6v-flash	48	9	36	100	0.00	0.00	131k	—
Claude Opus 4.7Retires Apr 16, 2027anthropic::claude-opus-4-7	48	84	49	10	5.00	25.00	1M	30.9
GLM 4.7 Flashxzai::glm-4.7-flashx	48	28	40	76	0.07	0.40	200k	—
Kimi K2.7 Codemoonshotai::kimi-k2.7-code	48	82	29	31	0.95	4.00	256k	—
Qwen3.8 Omni Flashalibaba::qwen3.8-omni-flash	48	72	23	47	0.15	0.47	992k	—
DeepSeek V4 Proalibaba::deepseek-v4-pro	48	83	30	28	2.40	4.80	1M	20.4
GLM 5.3 Flashxzai::glm-5.3-flashx	47	78	28	34	0.37	1.25	—	—
GPT 5openai::gpt-5	46	78	41	19	1.25	10.00	272k	11.4
Kimi K2.7 Codealibaba::kimi-k2.7-code	46	81	28	28	0.95	4.00	229k	—
Mistral Large 4.0mistral-ai::mistral-large-4-0	46	76	27	34	0.68	2.09	1M	—
GPT 6 Astraopenai::gpt-6-astra	46	76	48	12	10.00	50.00	922k	45.2
GPT 3.5 Turbo 16kRetires Oct 23, 2026openai::gpt-3.5-turbo-16k	46	9	93	37	3.00	4.00	16k	—
GPT 4 TurboRetires Oct 23, 2026openai::gpt-4-turbo	46	51	66	20	10.00	30.00	128k	7.0
GPT 4Retires Oct 23, 2026openai::gpt-4	45	77	53	6	30.00	60.00	8k	6.7
GPT 5.6 Solopenai::gpt-5.6-sol	45	84	35	16	4.00	20.00	922k	28.3
Qwen3.8 2.4t A95Balibaba::qwen3.8-2.4t-a95b	44	84	11	37	0.90	0.90	1M	39.9
O1Retires Oct 23, 2026openai::o1	44	78	54	0	15.00	60.00	200k	15.2
Grok 4.6xai::grok-4.6	44	84	11	37	2.00	6.00	500k	35.1
Qwen3.8 27Balibaba::qwen3.8-27b	44	69	19	43	0.02	0.90	1M	20.2
GLM 5.1zai::glm-5.1	44	76	23	31	1.40	4.40	200k	—
GLM 5.3 Flashtogether-ai::zai-org/GLM-5.3-Flash	44	75	12	43	0.15	0.50	1M	—
GLM 5.1alibaba::glm-5.1	44	76	32	22	1.40	4.40	203k	—
O1 (2024-12-17)Retires Oct 23, 2026openai::o1-2024-12-17	44	80	50	0	15.00	60.00	200k	15.2
GPT 5.5openai::gpt-5.5	43	84	39	5	5.00	30.00	1.1M	23.2
GLM 5.3 Flashzai::glm-5.3-flash	43	78	5	44	0.15	0.50	1M	—
Qwen3 VL 32B Thinkingalibaba::qwen3-vl-32b-thinking	42	65	31	31	0.16	2.87	131k	—
GLM 5 Turbozai::glm-5-turbo	41	76	20	27	1.20	4.00	200k	—
GLM 4.5 Xzai::glm-4.5-x	41	76	25	22	2.20	8.90	128k	—
Mistral Large 4mistral-ai::mistral-large-4	41	76	19	26	0.68	2.09	1M	—
Zai Glm 5.3mistral-ai::zai-glm-5-3	40	83	25	10	1.40	4.40	1M	—
Grok 4.7xai::grok-4.7	39	76	17	22	2.00	6.00	500k	46.4
Qwen3.8 Maxalibaba::qwen3.8-max	39	84	15	15	2.00	6.00	992k	40.2
GPT OSS 20Bgroq::openai/gpt-oss-20b	37	0	18	93	0.08	0.30	131k	9.0
Zai Glm 5mistral-ai::zai-glm-5	37	79	21	8	1.40	4.40	1M	—
Kimi K3moonshotai::kimi-k3	36	85	18	4	3.00	15.00	1M	—
Zai Glm (latest)mistral-ai::zai-glm-latest	36	77	21	9	1.40	4.40	1M	—
Kimi K2.6moonshotai::kimi-k2.6	35	82	5	18	0.95	4.00	256k	—
GLM 5zai::glm-5	34	78	10	12	1.00	3.20	200k	—
GLM 5.2alibaba::glm-5.2	33	80	10	9	1.40	4.40	1M	—
DeepSeek V4 Flash (0731)together-ai::deepseek-ai/DeepSeek-V4-Flash-0731	32	0	23	74	0.14	0.28	1M	18.9
GLM 5.2zai::glm-5.2	32	80	3	10	1.40	4.40	1M	—
GLM 5.3zai::glm-5.3	31	81	5	7	1.40	4.40	1M	—
C4ai Aya Vision 32Bcohere::c4ai-aya-vision-32b	—	69	32	—	—	—	16k	—
Command A Translate (08-2025)cohere::command-a-translate-08-2025	—	9	98	—	—	—	9k	—
Qwen Flashalibaba::qwen-flash	—	76	49	—	—	—	998k	—
Qwen3 Max (preview)alibaba::qwen3-max-preview	—	75	44	—	—	—	258k	—

224 models85 and above60 to 84below 60

About this data. Pricing and capability flags are synced daily from LiteLLM, PricePerToken and the vendors' own catalogs, then verified by our capability probe. Quality scores come from the benchmark scenarios published by Entity Enricher; speed and cost are relative to the models measured on the same scenario. Vendor list prices, before any Entity Enricher plan commission.

models.json How benchmark scores are computed Model management documentation