LLM Leaderboard 2026

434+ AI models ranked by our RunFree Score — a 0-100 composite of reasoning, coding, math and agentic benchmarks — alongside live API pricing and context windows. Right now, Qwen3 Max Thinking leads at 94.8.

Pricing updated August 14, 2026 · 13 models scored

Most intelligent
Qwen3 Max Thinking
RunFree 94.8
Best value
DeepSeek V4 Flash 0423
59.1 · $0.18/1M
Cheapest paid
Ling-2.6-flash
$0.01/1M tokens
Largest context
Grok 4.20
2M tokens

Full ranked, filterable table of AI models

#Model
1Qwen3 Max Thinking
94.8
$1.56
2Claude Opus 4.8
94.7
$10.00
3GLM 5.2
86.3
$1.83
4Claude Opus 4.7
85.7
$10.00
5GPT-5.5
78.8
$11.25
6Gemini 3.1 Pro Preview
78
$4.50
7DeepSeek V4 Pro
72.4
$1.46
8Claude Sonnet 4.6
66.2
$6.00
9Gemini 3 Flash Preview
63.5
$1.13
10DeepSeek V4 Flash 0423
59.1
$0.18
11Kimi K2 Thinking
45.2
$1.07
12Gemini 2.5 Pro
22.3
$3.44
13Llama 4 Maverick
0
$0.32
14Aion-1.0
$5.00
15Aion-1.0-Mini
$0.87
16Aion-2.0
$1.00
17Aion-3.0
$3.75
18Aion-3.0-Mini
$0.87
19Aion-RP 1.0 (8B)
$1.00
20Anthropic Claude Haiku Latest
$2.00
21Anthropic Claude Sonnet Latest
$4.00
22Claude 3 Haiku
$0.50
23Claude Fable 5
$20.00
24Claude Fable 5 (batch)
$10.00
25Claude Fable Latest
$20.00
26Claude Haiku 4.5
$2.00
27Claude Haiku 4.5 (batch)
$1.00
28Claude Opus 4
$30.00
29Claude Opus 4.1
$30.00
30Claude Opus 4.1 (batch)
$15.00
31Claude Opus 4.5
$10.00
32Claude Opus 4.5 (batch)
$5.00
33Claude Opus 4.6
$10.00
34Claude Opus 4.6 (batch)
$5.00
35Claude Opus 4.6 (Fast)
$60.00
36Claude Opus 4.7 (batch)
$5.00
37Claude Opus 4.7 (Fast)
$60.00
38Claude Opus 4.8 (batch)
$5.00
39Claude Opus 4.8 (Fast)
$20.00
40Claude Opus 5
$10.00
41Claude Opus 5 (batch)
$5.00
42Claude Opus 5 (Fast)
$20.00
43Claude Opus Latest
$10.00
44Claude Sonnet 4
$6.00
45Claude Sonnet 4.5
$6.00
46Claude Sonnet 4.5 (batch)
$3.00
47Claude Sonnet 4.6 (batch)
$3.00
48Claude Sonnet 5
$4.00
49Claude Sonnet 5 (batch)
$2.00
50Coder Large
$0.57
51Codestral 2508
$0.45
52Cogito v2.1 671B
$1.25
53Command A
$4.38
54Command R (08-2024)
$0.26
55Command R+ (08-2024)
$4.38
56Command R7B (12-2024)
$0.07
57Cydonia 24B V4.1
$0.35
58DeepSeek V3
$0.45
59DeepSeek V3 0324
$0.48
60DeepSeek V3.1
$0.42
61DeepSeek V3.1 Terminus
$0.44
62DeepSeek V3.2
$0.30
63DeepSeek V3.2 Exp
$0.30
64DeepSeek V4 Flash 0731
$0.18
65DeepSeek V4 Flash Latest
$0.12
66DeepSeek V4 Pro 0813
$0.54
67Devstral 2 2512
$0.80
68Dots3-Note Preview (free)
Free
69ERNIE 4.5 VL 424B A47B
$0.63
70Fugu Ultra
$11.25
71Gemini 2.5 Flash
$0.85
72Gemini 2.5 Flash (batch)
$0.42
73Gemini 2.5 Flash Lite
$0.17
74Gemini 2.5 Flash Lite (batch)
$0.09
75Gemini 2.5 Flash Lite Preview 09-2025
$0.17
76Gemini 2.5 Pro (batch)
$1.72
77Gemini 2.5 Pro Preview 05-06
$3.44
78Gemini 2.5 Pro Preview 06-05
$3.44
79Gemini 3 Flash Preview (batch)
$0.56
80Gemini 3.1 Flash Lite
$0.56
81Gemini 3.1 Flash Lite (batch)
$0.28
82Gemini 3.1 Flash Lite Preview
$0.56
83Gemini 3.1 Pro Preview (batch)
$2.25
84Gemini 3.1 Pro Preview Custom Tools
$4.50
85Gemini 3.5 Flash
$3.38
86Gemini 3.5 Flash (batch)
$1.69
87Gemini 3.5 Flash Lite
$0.85
88Gemini 3.5 Flash Lite (batch)
$0.42
89Gemini 3.6 Flash
$1.50
90Gemini 3.6 Flash (batch)
$0.75
91Gemini 3.7 Flash
$0.75
92Gemini 3.7 Flash (batch)
$0.38
93Gemma 2 27B
$0.65
94Gemma 3 12B
$0.07
95Gemma 3 27B
$0.17
96Gemma 3 4B
$0.06
97Gemma 3n 4B
$0.07
98Gemma 4 26B A4B
$0.19
99Gemma 4 26B A4B (free)
Free
100Gemma 4 31B
$0.16
101Gemma 4 31B (free)
Free
102GLM 4.5
$1.00
103GLM 4.5 Air
$0.31
104GLM 4.5V
$0.90
105GLM 4.6
$0.88
106GLM 4.6V
$0.45
107GLM 4.7
$0.74
108GLM 4.7 Flash
$0.14
109GLM 5
$1.35
110GLM 5 Turbo
$1.90
111GLM 5.1
$2.15
112GLM 5.2 (batch)
$1.07
113GLM 5V Turbo
$1.90
114Google Gemini Flash Latest
$0.75
115Google Gemini Pro Latest
$4.50
116GPT Chat Latest
$11.25
117GPT-3.5 Turbo
$0.75
118GPT-3.5 Turbo (batch)
$0.38
119GPT-3.5 Turbo (older v0613)
$1.25
120GPT-3.5 Turbo 16k
$3.25
121GPT-3.5 Turbo Instruct
$1.63
122GPT-4
$37.50
123GPT-4 Turbo
$15.00
124GPT-4 Turbo (batch)
$7.50
125GPT-4 Turbo Preview
$15.00
126GPT-4.1
$3.50
127GPT-4.1 (batch)
$1.75
128GPT-4.1 Mini
$0.70
129GPT-4.1 Mini (batch)
$0.35
130GPT-4.1 Nano
$0.17
131GPT-4.1 Nano (batch)
$0.09
132GPT-4o
$4.38
133GPT-4o (2024-05-13)
$7.50
134GPT-4o (2024-08-06)
$4.38
135GPT-4o (2024-11-20)
$4.38
136GPT-4o (batch)
$2.19
137GPT-4o Search Preview
$4.38
138GPT-4o-mini
$0.26
139GPT-4o-mini (2024-07-18)
$0.26
140GPT-4o-mini (batch)
$0.13
141GPT-4o-mini Search Preview
$0.26
142GPT-5
$3.44
143GPT-5 (batch)
$1.72
144GPT-5 Chat
$3.44
145GPT-5 Codex
$3.44
146GPT-5 Codex (batch)
$1.72
147GPT-5 Mini
$0.69
148GPT-5 Mini (batch)
$0.34
149GPT-5 Nano
$0.14
150GPT-5 Nano (batch)
$0.07
151GPT-5 Pro
$41.25
152GPT-5 Pro (batch)
$20.63
153GPT-5.1
$3.44
154GPT-5.1 (batch)
$1.72
155GPT-5.1 Chat
$3.44
156GPT-5.1-Codex
$3.44
157GPT-5.1-Codex-Max
$3.44
158GPT-5.1-Codex-Mini
$0.69
159GPT-5.2
$4.81
160GPT-5.2 (batch)
$2.41
161GPT-5.2 Chat
$4.81
162GPT-5.2 Pro
$57.75
163GPT-5.2 Pro (batch)
$28.88
164GPT-5.2-Codex
$4.81
165GPT-5.3 Chat
$4.81
166GPT-5.3-Codex
$4.81
167GPT-5.4
$5.63
168GPT-5.4 (batch)
$2.81
169GPT-5.4 Mini
$1.69
170GPT-5.4 Mini (batch)
$0.84
171GPT-5.4 Nano
$0.46
172GPT-5.4 Nano (batch)
$0.23
173GPT-5.4 Pro
$67.50
174GPT-5.4 Pro (batch)
$33.75
175GPT-5.5 (batch)
$5.63
176GPT-5.5 Pro
$67.50
177GPT-5.5 Pro (batch)
$33.75
178GPT-5.6 Luna
$0.22
179GPT-5.6 Luna (batch)
$0.22
180GPT-5.6 Luna Pro
$0.22
181GPT-5.6 Luna Pro (batch)
$0.22
182GPT-5.6 Sol
$11.25
183GPT-5.6 Sol (batch)
$5.63
184GPT-5.6 Sol Pro
$11.25
185GPT-5.6 Sol Pro (batch)
$5.63
186GPT-5.6 Terra
$2.25
187GPT-5.6 Terra (batch)
$2.25
188GPT-5.6 Terra Pro
$2.25
189GPT-5.6 Terra Pro (batch)
$2.25
190gpt-oss-120b
$0.07
191gpt-oss-120b (free)
Free
192gpt-oss-20b
$0.06
193gpt-oss-20b (free)
Free
194gpt-oss-safeguard-20b
$0.13
195Granite 4.0 Micro
$0.04
196Granite 4.1 8B
$0.06
197Grok 4.20
$1.56
198Grok 4.20 Multi-Agent
$1.56
199Grok 4.3
$1.56
200Grok 4.5
$3.00
201Grok 4.6
$3.00
202Grok Build 0.1
$1.25
203Grok Latest
$3.00
204Hermes 3 405B Instruct
$1.00
205Hermes 3 405B Instruct (free)
Free
206Hermes 3 70B Instruct
$0.70
207Hermes 4 405B
$1.50
208Hermes 4 70B
$0.20
209Hunyuan A13B Instruct
$0.25
210Hy3
$0.23
211Hy3 (free)
Free
212Hy3 preview
$0.10
213Inflection 3 Pi
$4.38
214Inflection 3 Productivity
$4.38
215Inkling
$1.72
216Inkling (batch)
$0.88
217Inkling Small
$0.64
218Jamba Large 1.7
$3.50
219KAT-Coder-Air V2.5
$0.26
220KAT-Coder-Pro V2
$0.52
221KAT-Coder-Pro V2.5
$1.29
222Kimi K2 0711
$1.00
223Kimi K2 0905
$1.07
224Kimi K2.5
$1.14
225Kimi K2.6
$1.04
226Kimi K2.7 Code
$1.41
227Kimi K2.7 Code (batch)
$0.86
228Kimi K3
$6.00
229Laguna M.1
$0.25
230Laguna M.1 (free)
Free
231Laguna S 2.1
$0.11
232Laguna S 2.1 (free)
Free
233Laguna XS 2.1
$0.07
234Laguna XS 2.1 (free)
Free
235Laguna XS.2
$0.13
236Laguna XS.2 (free)
Free
237LFM2-24B-A2B
$0.05
238LFM2.5-1.2B-Instruct (free)
Free
239LFM2.5-1.2B-Thinking (free)
Free
240LFM2.5-2.6B (free)
Free
241Ling 3.0 Tiny (free)
Free
242Ling-2.6-1T
$0.21
243Ling-2.6-flash
$0.01
244Ling-3.0-flash
$0.03
245Ling-3.0-flash (free)
Free
246Llama 3 8B Instruct
$0.14
247Llama 3 8B Lunaris
$0.04
248Llama 3.1 70B Hanami x1
$3.00
249Llama 3.1 70B Instruct
$0.40
250Llama 3.1 8B Instruct
$0.06
251Llama 3.1 Euryale 70B v2.2
$0.85
252Llama 3.2 11B Vision Instruct
$0.34
253Llama 3.2 1B Instruct
$0.07
254Llama 3.2 3B Instruct
$0.12
255Llama 3.2 3B Instruct (free)
Free
256Llama 3.3 70B Instruct
$0.15
257Llama 3.3 70B Instruct (free)
Free
258Llama 3.3 Euryale 70B
$0.68
259Llama 3.3 Nemotron Super 49B V1.5
$0.40
260Llama 4 Scout
$0.15
261Llama Guard 4 12B
$0.18
262LongCat 2.0
$0.52
263Magnum v4 72B
$3.50
264Mercury 2
$0.38
265MiMo-V2.5
$0.18
266MiMo-V2.5-Pro
$0.54
267MiniMax M1
$0.96
268MiniMax M2
$0.45
269MiniMax M2-her
$0.52
270MiniMax M2.1
$0.52
271MiniMax M2.5
$0.39
272MiniMax M2.7
$0.52
273MiniMax M3
$0.52
274MiniMax M3 (batch)
$0.26
275MiniMax-01
$0.43
276Ministral 3 14B 2512
$0.20
277Ministral 3 3B 2512
$0.10
278Ministral 3 8B 2512
$0.15
279Mistral Large
$3.00
280Mistral Large 2407
$3.00
281Mistral Large 3 2512
$0.75
282Mistral Medium 3
$0.80
283Mistral Medium 3.1
$0.80
284Mistral Medium 3.5
$3.00
285Mistral Nemo
$0.02
286Mistral Small 3
$0.06
287Mistral Small 3.1 24B
$0.40
288Mistral Small 3.2 24B
$0.13
289Mistral Small 4
$0.26
290Mixtral 8x22B Instruct
$3.00
291MoonshotAI Kimi Latest
$5.60
292Morph V3 Fast
$0.90
293Morph V3 Large
$1.15
294Muse Glimmer 30B
$0.64
295Muse Spark 1.1
$2.00
296Muse Spark 1.2
$2.00
297MythoMax 13B
$0.06
298Namazu
$1.71
299Nemotron 3 Nano 30B A3B
$0.09
300Nemotron 3 Nano 30B A3B (free)
Free
301Nemotron 3 Nano Omni (free)
Free
302Nemotron 3 Super
$0.16
303Nemotron 3 Super (free)
Free
304Nemotron 3 Ultra
$1.35
305Nemotron 3 Ultra (batch)
$0.67
306Nemotron 3 Ultra (free)
Free
307Nemotron 3.5 Content Safety (free)
Free
308Nemotron 3.5 Lightning
$0.14
309Nemotron 3.5 Lightning (free)
Free
310Nemotron Nano 12B 2 VL (free)
Free
311Nemotron Nano 9B V2 (free)
Free
312Nex-N2-Mini
$0.04
313Nex-N2-Pro
$0.44
314North Mini Code (free)
Free
315Nova 2 Lite
$0.85
316Nova Lite 1.0
$0.10
317Nova Micro 1.0
$0.06
318Nova Premier 1.0
$5.00
319Nova Pro 1.0
$1.40
320o1
$26.25
321o1 (batch)
$13.13
322o1-pro
$263
323o1-pro (batch)
$131
324o3
$3.50
325o3 (batch)
$1.75
326o3 Deep Research
$17.50
327o3 Mini
$1.93
328o3 Mini (batch)
$0.96
329o3 Mini High
$1.93
330o3 Mini High (batch)
$0.96
331o3 Pro
$35.00
332o3 Pro (batch)
$17.50
333o4 Mini
$1.93
334o4 Mini (batch)
$0.96
335o4 Mini Deep Research
$3.50
336o4 Mini High
$1.93
337o4 Mini High (batch)
$0.96
338Olmo 3 32B Think
$0.24
339OpenAI GPT Latest
$11.25
340OpenAI GPT Mini Latest
$1.69
341Palmyra X5
$1.95
342Perceptron Mk1
$0.49
343Phi 4
$0.09
344Phi 4 Mini Instruct
$0.15
345Qwen Plus 0728
$0.39
346Qwen Plus 0728 (thinking)
$0.60
347Qwen-Plus
$0.39
348Qwen2.5 72B Instruct
$0.37
349Qwen2.5 7B Instruct
$0.13
350Qwen2.5 Coder 32B Instruct
$0.74
351Qwen2.5 VL 72B Instruct
$0.38
352Qwen3 14B
$0.15
353Qwen3 235B A22B
$0.80
354Qwen3 235B A22B Instruct 2507
$0.21
355Qwen3 235B A22B Thinking 2507
$0.75
356Qwen3 30B A3B
$0.21
357Qwen3 30B A3B Instruct 2507
$0.08
358Qwen3 30B A3B Thinking 2507
$0.75
359Qwen3 32B
$0.13
360Qwen3 8B
$0.20
361Qwen3 Coder 30B A3B Instruct
$0.12
362Qwen3 Coder 480B A35B
$0.47
363Qwen3 Coder 480B A35B (free)
Free
364Qwen3 Coder Flash
$0.39
365Qwen3 Coder Next
$0.29
366Qwen3 Coder Plus
$1.30
367Qwen3 Max
$1.56
368Qwen3 Next 80B A3B Instruct
$0.35
369Qwen3 Next 80B A3B Instruct (free)
Free
370Qwen3 Next 80B A3B Thinking
$0.41
371Qwen3 VL 235B A22B Instruct
$0.46
372Qwen3 VL 235B A22B Thinking
$1.30
373Qwen3 VL 30B A3B Instruct
$0.23
374Qwen3 VL 30B A3B Thinking
$0.75
375Qwen3 VL 32B Instruct
$0.18
376Qwen3 VL 8B Instruct
$0.20
377Qwen3 VL 8B Thinking
$0.66
378Qwen3.5 397B A17B
$1.27
379Qwen3.5 Plus 2026-02-15
$0.58
380Qwen3.5 Plus 2026-04-20
$0.67
381Qwen3.5-122B-A10B
$0.82
382Qwen3.5-27B
$0.54
383Qwen3.5-35B-A3B
$0.62
384Qwen3.5-9B
$0.11
385Qwen3.5-Flash
$0.11
386Qwen3.6 27B
$1.35
387Qwen3.6 35B A3B
$0.36
388Qwen3.6 Flash
$0.42
389Qwen3.6 Max Preview
$2.31
390Qwen3.6 Plus
$0.73
391Qwen3.7 Flash
$0.06
392Qwen3.7 Max
$2.21
393Qwen3.7 Plus
$0.56
394Qwen3.8 2.4T A95B
$3.00
395Qwen3.8 Max
$3.00
396R1
$1.15
397R1 0528
$0.91
398R1 Distill Llama 70B
$0.80
399Reka Edge
$0.10
400Reka Flash 3
$0.13
401Relace Apply 3
$0.95
402Relace Search
$1.50
403ReMM SLERP 13B
$0.50
404Ring-2.6-1T
$0.21
405Rocinante 12B
$0.31
406Saba
$0.30
407Sakana Namazu
$1.71
408Seed 1.6
$0.69
409Seed 1.6 Flash
$0.13
410Seed 2.1 Turbo
$1.00
411Seed-2.0-Code
$1.13
412Seed-2.0-Lite
$0.69
413Seed-2.0-Mini
$0.17
414Skyfall 36B V2
$0.61
415Solar Pro 3
$0.26
416Solar Pro 4
$0.05
417Sonar
$1.00
418Sonar Deep Research
$3.50
419Sonar Pro
$6.00
420Sonar Pro Search
$6.00
421Sonar Reasoning Pro
$3.50
422Step 3.5 Flash
$0.15
423Step 3.7 Flash
$0.44
424Switchpoint Router
$1.49
425Trinity Large Thinking
$0.38
426Trinity Mini
$0.07
427UI-TARS 7B
$0.13
428Uncensored
$0.38
429Uncensored (free)
Free
430UnslopNemo 12B
$0.40
431Virtuoso Large
$0.86
432Voxtral Small 24B 2507
$0.15
433Weaver (alpha)
$0.56
434WizardLM-2 8x22B
$0.62

Showing 434 of 434 models. Click a column to sort, a model to open its card.

Models without enough public benchmark data are unscored. Speed (tok/s) shows where measured. Data as of August 14, 2026; see methodology.

Top 15 by RunFree Score

Loading chart…

Intelligence vs price

Loading chart…

Up and to the left is better: smarter for less. Log price scale.

Explore by category

AI model leaderboard — FAQ

Which is the most intelligent AI model right now?

By our RunFree Score, Qwen3 Max Thinking ranks highest at 94.8/100, a composite of reasoning, coding, math and agentic benchmarks. See the full ranking above.

What is the best value AI model (smart and cheap)?

DeepSeek V4 Flash 0423 offers one of the best intelligence-per-dollar ratios, scoring 59.1 at about $0.18/1M tokens (blended). The intelligence-vs-price chart above shows the full picture.

Which is the cheapest AI model?

Ling-2.6-flash is among the cheapest paid models at roughly $0.01/1M tokens (blended 3:1 input:output). Several models are also free to use.

Which model has the largest context window?

Grok 4.20 has one of the largest context windows in the list. Sort the table by Context to compare them all.

How are these AI models scored?

Each model gets a RunFree Score: we normalize its results on public benchmarks (GPQA, SWE-Bench, AIME and more), average them within reasoning, coding, math and agentic categories, then weight the categories. The full formula is on our methodology page.

How often is this leaderboard updated?

Model details and API pricing refresh automatically every hour from OpenRouter. Benchmark scores are added from each model's official source as it publishes them, with the date shown.