Leaderboard

Overall Rankings

The Podium Score — a weighted blend of arena preference, benchmark averages, intelligence indices and expert evaluations across all five tracked leaderboards.

Claude Mythos Preview

Overall767 Coding469 Math90 Reasoning483 Agentic89 Knowledge482 Multimodal452 Coding Agents68 Scientific Reasoning96 Multilingual12 Writing95 Chat & Assistants95 Research99 Tool Calling45 Long Context116 Speed472 Value471 Open Weights183

767 models

#	Model	Podium Score	Arena Elo	Intelligence	Coding	Speed	Price (out)
01	Claude Mythos Preview Anthropicreasoningpreview	97.4	—	—	80.9	80 t/s	$15/M
02	Claude 5.5 Sonnet Anthropicreasoning	94.8	1520	95.0	91.5	94 t/s	$15/M
03	Kimi K3.1 Pro Moonshot AIOpenreasoning	94.2	1490	68.0	72.0	45 t/s	$20/M
4	Eleven Multilingual v3 ElevenLabs	94.0	1485	94.0	0.0	200 t/s	$0.05/M
5	FLUX.2 Pro Black Forest Labs	93.8	1480	94.0	0.0	30 t/s	$0.08/M
6	Gemini 4 Argon Googlereasoningpreview	93.6	1505	94.0	88.0	88 t/s	$10/M
7	Claude Fable 5 Anthropicreasoning	93.4	1509	60.0	84.1	71 t/s	$50/M
8	GPT-Image 2 OpenAI	93.1	1470	93.0	0.0	25 t/s	$0.09/M
9	Grok Imagine Quality xAI	92.6	1465	93.0	0.0	34 t/s	$0.06/M
10	ElevenLabs Scribe v2 ElevenLabs	92.5	1460	93.0	0.0	240 t/s	$0.016/M
11	GPT-6.1 Sol OpenAIreasoning	92.4	1495	93.0	89.0	75 t/s	$20/M
12	Cartesia Ink Whisper Cartesia	91.8	1450	92.0	0.0	260 t/s	$0.012/M
13	Kimi K3.1 Highspeed Moonshot AIOpenreasoning	91.5	1455	60.0	60.0	130 t/s	$8/M
14	Gemini 3.1 Pro Preview Googlereasoningpreview	90.8	1465	91.0	85.5	105 t/s	$5/M
15	FLUX.2 Dev Black Forest LabsOpen	90.4	1440	90.0	0.0	28 t/s	$0.03/M
16	Voxtral 3 TTS Mistral	90.2	1438	90.0	0.0	165 t/s	$0.03/M
17	Mistral Large 4 Mistralreasoning	89.8	1450	90.0	84.5	92 t/s	$6/M
18	Qwen Audio 3.1 TTS+ AlibabaOpen	89.4	1430	89.0	0.0	140 t/s	$0.02/M
19	FLUX.2 Max Independent	89.2	1435	89.0	0.0	35 t/s	$0.05/M
20	LTX-2.3 Pro Lightricks	89.1	1425	89.0	0.0	18 t/s	$0.12/M
21	Claude Fable 5.1 (XHigh) Anthropicreasoning	89.0	—	—	88.0	78 t/s	$15/M
22	Step Audio 2 StepFun	89.0	1422	89.0	0.0	150 t/s	$0.024/M
23	GLM-4.5 Air Zhipu AIOpenreasoning	88.9	1420	58.0	55.0	96 t/s	$1.1/M
24	Kling 3.0 Pro Kwai	88.6	1420	88.0	0.0	25 t/s	$0.1/M
25	Ling 3.1 Flash Ling	88.5	1418	56.0	50.0	175 t/s	$0.8/M
26	Claude Fable 5.1 Anthropicreasoning	88.4	—	—	95.5	85 t/s	$15/M
27	MiMo v2.6 Flash XiaomiOpen	88.4	1425	88.0	86.0	118 t/s	$0.3/M
28	FLUX.2 Klein 9B Black Forest LabsOpen	88.2	1405	88.0	0.0	55 t/s	$0.02/M
29	Qwen3 TTS Flash Alibaba	88.1	1408	88.0	0.0	230 t/s	$0.01/M
30	NVIDIA Nemotron 3.5 Super-VL NVIDIAOpen	87.8	1418	88.0	83.0	110 t/s	$1.2/M
31	Simba 3.2 Independentreasoning	87.8	1400	62.0	62.0	62 t/s	$10/M
32	Claude 5.5 Haiku Anthropicreasoning	87.5	1410	88.0	84.0	145 t/s	$4/M
33	Wan 2.2 A14B AlibabaOpen	87.4	1415	87.0	0.0	15 t/s	$0.06/M
34	ElevenLabs v4 Turbo Independent	87.1	1395	87.0	0.0	220 t/s	$0.03/M
35	GPT-6 Astra (xhigh) OpenAIreasoning	87.0	—	—	60.0	76 t/s	$50/M
36	Claude Fable 5.1 (High) Anthropicreasoning	86.5	—	—	88.0	92 t/s	$15/M
37	Deepgram Flux Independent	86.5	1380	86.0	0.0	260 t/s	$0.015/M
38	FLUX.2 Klein 4B Black Forest LabsOpen	86.5	1380	87.0	0.0	90 t/s	$0.01/M
39	GPT-6 Astra OpenAIreasoning	86.2	1498	61.0	67.2	82 t/s	$50/M
40	LTX-2.3 Fast Lightricks	86.2	1385	86.0	0.0	60 t/s	$0.05/M
41	Gemini 3.1 Flash Lite Preview Googlepreview	85.4	1365	85.0	76.0	210 t/s	$0.3/M
42	GPT-6 Astra (high) OpenAIreasoning	85.0	—	—	60.0	90 t/s	$50/M
43	GPT-6 Luna OpenAIreasoning	84.5	—	—	62.0	120 t/s	$20/M
44	Claude Opus 5.5 (XHigh) Anthropicreasoning	84.5	—	—	75.0	62 t/s	$25/M
45	GPT-6 Luna (xhigh) OpenAIreasoning	84.0	—	—	55.0	118 t/s	$20/M
46	Claude Opus 5.5 Anthropicreasoning	84.0	—	—	85.0	68 t/s	$25/M
47	Claude Fable 5.1 (Medium) Anthropicreasoning	84.0	—	—	88.0	104 t/s	$15/M
48	Kimi K3 Moonshot AIOpenreasoning	83.3	1485	57.0	61.5	37 t/s	$15/M
49	Claude Opus 5.5 (High) Anthropicreasoning	82.5	—	—	75.0	74 t/s	$25/M
50	GPT-6 Luna (high) OpenAIreasoning	82.0	—	—	55.0	128 t/s	$20/M
51	GPT-6 Astra (medium) OpenAIreasoning	81.5	—	—	60.0	98 t/s	$50/M
52	Claude Opus 5 Anthropic	81.4	1492	61.0	70.4	60 t/s	$25/M
53	GPT-5.6 Sol OpenAI	80.8	1483	59.0	64.8	72 t/s	$30/M
54	Claude Fable 5.1 (Low) Anthropicreasoning	80.0	—	—	88.0	118 t/s	$15/M
55	Qwen3.8 Max Alibaba	79.8	1496	—	50.3	55 t/s	$2/M
56	Claude Opus 5.5 (Medium) Anthropicreasoning	79.5	—	—	75.0	82 t/s	$25/M
57	GPT-6 Luna (medium) OpenAIreasoning	78.5	—	—	55.0	138 t/s	$20/M
58	GPT-6 Sol (xhigh) OpenAIreasoning	78.5	—	—	50.0	210 t/s	$4/M
59	GPT-6 Sol OpenAIreasoning	78.0	—	—	55.0	220 t/s	$4/M
60	GPT-6 Astra (low) OpenAIreasoning	78.0	—	—	60.0	110 t/s	$50/M
61	GPT-6 Sol (high) OpenAIreasoning	77.0	—	—	50.0	226 t/s	$4/M
62	Claude Opus 4.8 Anthropic	76.0	1484	55.7	58.0	50 t/s	$15/M
63	Claude Opus 5.5 (Low) Anthropicreasoning	75.5	—	—	75.0	92 t/s	$25/M
64	Claude Opus 4 6 Thinking Anthropicreasoning	75.0	—	—	—	50 t/s	$15/M
65	Claude Opus 4 7 Thinking Anthropicreasoning	75.0	—	—	—	50 t/s	$15/M
66	Claude Opus 5 Max Anthropic	75.0	—	—	—	50 t/s	$15/M
67	GPT-6 Luna (low) OpenAIreasoning	74.5	—	—	55.0	150 t/s	$20/M
68	Kimi K3 Max Moonshot AIreasoning	74.0	—	—	—	50 t/s	$3/M
69	Claude Opus 4 8 Thinking Anthropicreasoning	74.0	—	—	—	50 t/s	$15/M
70	GPT 5.6 Sol Xhigh OpenAI	74.0	—	—	—	50 t/s	$10/M
71	GPT 5.5 High OpenAI	74.0	—	—	—	50 t/s	$10/M
72	GPT 5.4 High OpenAI	74.0	—	—	—	50 t/s	$10/M
73	Gemini 3.5 Flash High Google	74.0	—	—	—	50 t/s	$5/M
74	GPT 5.2 Chat Latest 20260210 OpenAI	74.0	—	—	—	50 t/s	$10/M
75	Qwen3.7 Max Preview Alibaba	74.0	—	—	—	50 t/s	$2/M
76	Grok 4.20 Beta1 xAI	74.0	—	—	—	50 t/s	$15/M
77	Gemini 3.5 Flash Medium Google	74.0	—	—	—	50 t/s	$5/M
78	GPT 5.5 Instant OpenAI	74.0	—	—	—	50 t/s	$10/M
79	Claude Opus 4 5 20251101 Thinking 32k Anthropicreasoning	74.0	—	—	—	50 t/s	$15/M
80	Grok 4.20 Beta 0309 Reasoning xAIreasoning	74.0	—	—	—	50 t/s	$15/M
81	Grok 4.20 Multi Agent Beta 0309 xAI	74.0	—	—	—	50 t/s	$15/M
82	GPT-6 Sol (medium) OpenAIreasoning	74.0	—	—	50.0	238 t/s	$4/M
83	Glm 5.2 Max Z.ai	73.0	—	—	—	50 t/s	$3/M
84	Claude Opus 4 5 20251101 Anthropic	73.0	—	—	—	50 t/s	$15/M
85	GPT 5.6 Terra Xhigh OpenAI	73.0	—	—	—	50 t/s	$10/M
86	Grok 4.1 Thinking xAIreasoning	73.0	—	—	—	50 t/s	$15/M
87	Qwen3.5 Max Preview Alibaba	73.0	—	—	—	50 t/s	$2/M
88	Qwen3.6 Max Preview Alibaba	73.0	—	—	—	50 t/s	$2/M
89	Grok 4.1 xAI	73.0	—	—	—	50 t/s	$15/M
90	Dola Seed 2.0 Pro Unknown	73.0	—	—	—	50 t/s	$3/M
91	Claude Sonnet 4 5 20250929 Thinking 32k Anthropicreasoning	73.0	—	—	—	50 t/s	$15/M
92	Claude Sonnet 4 5 20250929 Anthropic	73.0	—	—	—	50 t/s	$15/M
93	GPT 5.1 High OpenAI	73.0	—	—	—	50 t/s	$10/M
94	Deepseek V4 Pro High Preview DeepSeek	73.0	—	—	—	50 t/s	$1.1/M
95	GPT 5.6 Luna Xhigh OpenAI	73.0	—	—	—	50 t/s	$10/M
96	Kimi K2.5 Thinking Moonshot AIreasoning	73.0	—	—	—	50 t/s	$3/M
97	Claude Opus 4 1 20250805 Thinking 16k Anthropicreasoning	72.0	—	—	—	50 t/s	$15/M
98	Ernie 5.0 Preview 1203 Baidu	72.0	—	—	—	50 t/s	$3/M
99	GPT 5.3 Chat Latest OpenAI	72.0	—	—	—	50 t/s	$10/M
100	GPT 5.4 Mini High OpenAI	72.0	—	—	—	50 t/s	$10/M

Podium Score is a weighted blend of five leaderboards. See Methodology for details.

Model Name

Provider

Podium Score0.0

Context128K

Price (1M out)$0/M

Speed0 t/s

Architecture & Highlights

Model overview and workload profile.

Quickstart cURL

curl https://api.openrouter.ai/api/v1/chat/completions ...