Skip to content

Text-Based Models (LLM)

Updated

The chat models behind writing, research and everyday questions, scored on hard tests and blind head-to-head votes.

Text model leaderboard

416 models · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

20 of 416 models in the chart · ·

All models

Compare#ModelCreatorLicenceInput / 1MScoreFrom votes From tests · countVotes
1Gemini 4 Argon (High)GoogleProprietary$2.00774699 871 · 24,904
2gpt-5.6-sol-xhigh OpenAIProprietary$5.00728546 846 · 540,442
3Gemini 3.7 Flash (High)GoogleProprietary$0.75700557 873 · 227,232
4Claude Opus 4.6 (High) AnthropicProprietary$5.00653620 684 · 1081,394
5deepseek-v4.1-flash-maxDeepSeekMIT$0.22648506 769 · 412,793
6gpt-5.6-terra-xhigh OpenAIProprietary$2.00648475 790 · 543,271
7Muse Wonder (Max)MetaProprietary$4.00643643 –3,247
8Claude Opus 4.6 AnthropicProprietary$5.00641596 684 · 1086,071
9Claude Opus 5.5 (High) AnthropicProprietary$4.00640640 –8,300
10gpt-6-astra-max OpenAIProprietary$10.00632516 813 · 212,163
11Claude Fable 5.1 (Max) AnthropicProprietary$10.00617617 –14,590
12qwen3.8-maxAlibabaProprietary$1.65605536 672 · 627,766
13Claude Fable 5 (High) AnthropicProprietary$10.00602622 561 · 242,004
14Gemini 3.8 Flash (High)GoogleProprietary$0.75593593 –37,454
15gpt-5.5-high OpenAIProprietary$5.00590532 646 · 869,401
16Muse Spark 1.3 (Max)MetaProprietary$0.10585585 –17,561
17Gemini 3.1 Pro PreviewGoogleProprietary$2.00580554 606 · 6127,649
18gpt-5.5 OpenAIProprietary$5.00580514 646 · 870,985
19Muse Spark 1.2 (xHigh)MetaProprietary$0.10579579 –8,248
20Muse Spark 1.1MetaProprietary$1.25568568 –42,810
21Claude Opus 5 (Max) AnthropicProprietary$5.00567567 –32,495
22Claude Opus 5 (High) AnthropicProprietary$5.00567567 –66,824
23claude-opus-4-8-high AnthropicProprietary$5.00566533 600 · 564,100
24Kimi K3 (Max) Moonshot AIKimi K3 license$2.85553555 548 · 232,795
25claude-opus-4-8 AnthropicProprietary$5.00551504 600 · 565,172
26gpt-5.4-high OpenAIProprietary$2.50546508 585 · 1264,776
27gpt-6.1-sol-max OpenAIProprietary$2.00542542 –6,320
28Claude Opus 4.7 (High) AnthropicProprietary$5.00538612 467 · 665,116
29gemini-3.6-flash-highGoogleProprietary$1.50537537 –36,122
30gpt-5.6-luna-xhigh OpenAIProprietary$0.20536426 655 · 541,109
31gemini-3.5-flash-highGoogleProprietary$1.50534517 551 · 648,486
32glm-5.2-max Z.aiMIT$0.75532510 555 · 649,820
33gemini-3.5-flash-mediumGoogleProprietary$1.50530510 551 · 647,292
34Gemini 3 ProGoogleProprietary–527549 507 · 1042,072
35gpt-5.4 OpenAIProprietary$2.50525468 585 · 1267,870
36mimo-v2.6-proXiaomiMIT$0.43524524 –4,075
37Claude Opus 4.7 AnthropicProprietary$5.00523582 467 · 666,216
38glm-5.3-max Z.aiMIT$1.20521521 –22,543
39Muse SparkMetaProprietary–516563 472 · 514,150
40claude-sonnet-4-6 AnthropicProprietary$3.00513496 530 · 1170,931
41gpt-5.2-chat-latest-20260210 OpenAIProprietary–510510 –35,999
42claude-sonnet-5.5-xhigh AnthropicProprietary$2.00507507 –6,831
43grok-4.20-beta1 xAIProprietary–506506 –27,908
44qwen3.7-max-previewAlibabaProprietary–505505 –3,934
45claude-opus-4-5-20251101-high-32k AnthropicProprietary–502502 –37,509
46claude-opus-4-5-20251101 AnthropicProprietary–500486 514 · 672,899
47glm-5.3-flash Z.aiMIT$0.15498503 489 · 232,925
48gpt-5.2-high OpenAIProprietary$1.75496379 636 · 1249,655
49grok-4.20-beta-0309-reasoning xAIProprietary–494494 –66,436
50gpt-5.2 OpenAIProprietary$1.75493374 636 · 1283,855
51grok-4.20-multi-agent-beta-0309 xAIProprietary–489489 –64,946
52gemini-3-flashGoogleProprietary$0.50488499 477 · 1031,325
53ernie-5.1BaiduProprietary–477477 –39,468
54grok-4.1-thinking xAIProprietary–470470 –66,509
55deepseek-v4-pro-high-20260813DeepSeekMIT–468468 –9,800
56qwen3.5-max-previewAlibabaProprietary–467467 –22,600
57kimi-k2.6 Moonshot AIModified MIT$0.75464454 475 · 740,013
58grok-4.5 xAIProprietary$2.00463472 446 · 239,896
59gemini-3-flash (thinking-minimal)GoogleProprietary$0.50461445 477 · 1091,039
60claude-sonnet-5-high AnthropicProprietary$2.00455455 –49,595
61qwen3.6-max-previewAlibabaProprietary–453453 –5,426
62glm-5.1 Z.aiMIT$1.05450470 430 · 762,889
63gpt-6-sol-max OpenAIProprietary$2.00448448 –12,466
63grok-4.1 xAIProprietary–448448 –68,648
64qwen3.7-plusAlibabaProprietary–445437 454 · 1542,075
65deepseek-v4-proDeepSeekMIT–444444 –57,594
66glm-5 Z.aiMIT$1.00442442 –29,272
67claude-sonnet-4-5-20250929-high-32k AnthropicProprietary–439439 –83,940
68dola-seed-2.0-proByteDanceProprietary–438438 –79,140
69deepseek-v4-pro-high-previewDeepSeekMIT–434434 –54,902
70gemini-3.5-flash-liteGoogleProprietary$0.30433433 –35,851
71grok-4.6-high xAIProprietary$2.00433433 –28,965
72kimi-k2.5-thinking Moonshot AIModified MIT–431417 446 · 974,759
73gpt-5.1-high OpenAIProprietary$1.25427437 417 · 641,651
74inklingThinkyApache 2.0$0.95426390 466 · 440,648
75qwen3.6-plusAlibabaProprietary$0.50423396 453 · 2248,165
76mimo-v2.6-flashXiaomiMIT$0.14421421 –10,917
77hy3TencentApache 2.0$0.14419428 409 · 412,208
78gpt-5.3-chat-latest OpenAIProprietary$1.75418418 –34,345
79claude-opus-4-1-20250805-thinking-16k AnthropicProprietary–417417 –49,542
80ernie-5.0-preview-1203BaiduProprietary–413413 –9,806
81mimo-v2-proXiaomiProprietary–411411 –25,447
82Step 5 PreviewStepfunProprietary–409409 –7,116
83ernie-5.0-0110BaiduProprietary–406406 –36,487
84gpt-5.5-instant OpenAIProprietary$5.00405500 279 · 227,158
85glm-4.7 Z.aiMIT$0.40404391 418 · 612,253
86qwen3.5-397b-a17bAlibabaApache 2.0$0.45402392 413 · 2193,567
87gpt-5-high OpenAIProprietary–402373 434 · 1331,722
88gpt-4.5-preview-2025-02-27 OpenAIProprietary–401401 –14,547
89gpt-5.1 OpenAIProprietary$1.25400383 417 · 644,434
90grok-4.7-xhigh xAIProprietary$2.00399399 –11,591
91qwen3.8-27bAlibabaApache 2.0$0.40398381 417 · 523,294
92gpt-6-luna-max OpenAIProprietary$0.10396396 –49,617
93chatgpt-4o-latest-20250326 OpenAIProprietary–395395 –81,914
94grok-4.3 xAIProprietary$1.25392392 –71,347
95minimax-m3MiniMaxMiniMax Community License$0.28391391 –63,973
96claude-sonnet-4-5-20250929 AnthropicProprietary$3.00387434 346 · 682,688
97gemma-4-31bGoogleApache 2.0$0.09384425 348 · 86,147
98deepseek-v4-flash-high-previewDeepSeekMIT–383383 –51,809
99longcat-flash-chat-2602-expMeituanProprietary–377377 –29,291
100deepseek-v4-flashDeepSeekMIT–375375 –51,987
101Inkling SmallThinkyApache 2.0$0.30374301 476 · 732,304
102qwen3-max-previewAlibabaProprietary–371371 –27,370
103mimo-v2.5XiaomiMIT$0.17370370 –47,362
104glm-5v-turbo Z.aiProprietary–370370 –10,482
105mistral-large-4MistralProprietary$0.68364364 –7,451
106mimo-v2-omniXiaomiProprietary–362362 –20,619
107kimi-k2.5-instant Moonshot AIModified MIT–361361 –8,376
108grok-4-1-fast-reasoning xAIProprietary$0.20361361 –57,541
109kimi-k2-thinking-turbo Moonshot AIModified MIT–360360 –63,368
110gemma-4-26b-a4bGoogleApache 2.0$0.07356380 335 · 66,094
111gpt-5-chat OpenAIProprietary–351351 –31,188
111gpt-5.4-mini-high OpenAIProprietary$0.75351408 305 · 863,449
112claude-opus-4-20250514-thinking-16k AnthropicProprietary–350350 –35,904
113amazon-nova-experimental-chat-26-02-10AmazonProprietary–350350 –3,526
114nvidia-nemotron-3-ultra-550b-a55b-nvfp4NVIDIAOpenMDW-1.1–350350 –11,567
115step-3.5-flashStepfunApache 2.0$0.10347281 440 · 360,332
116deepseek-v3.2DeepSeekMIT$0.28346346 –48,112
117muse-glimmerMetaApache-2.0–346346 –3,897
118deepseek-v3.2-exp-thinkingDeepSeekMIT–346347 344 · 78,998
119qwen3-max-2025-09-23AlibabaProprietary–343343 –9,027
120mimo-v2.5-proXiaomiMIT$0.43343478 259 · 1375,721
121deepseek-v3.2-expDeepSeekMIT–341339 344 · 712,004
122gemini-2.5-proGoogleProprietary$1.25341403 293 · 7125,366
123deepseek-v3.2-thinkingDeepSeekMIT$0.28341341 –42,071
124glm-4.6 Z.aiMIT$0.50339345 333 · 435,824
125qwen3.5-122b-a10bAlibabaApache 2.0$0.29339327 351 · 2229,732
126deepseek-r1-0528DeepSeekMIT$0.50337339 336 · 918,167
127solar-pro4UpstageProprietary$0.30335270 428 · 321,281
128grok-4-fast-chat xAIProprietary–332332 –6,340
128kimi-k2-0905-preview Moonshot AIModified MIT–332332 –11,589
129ernie-5.0-preview-1022BaiduProprietary–331331 –4,753
130claude-opus-4-1-20250805 AnthropicProprietary–331412 273 · 577,238
131kimi-k2-0711-preview Moonshot AIModified MIT–330330 –27,146
132qwen3.5-27bAlibabaApache 2.0$0.26330311 351 · 2228,671
133deepseek-v3.1-terminus-thinkingDeepSeekMIT–326326 –3,375
134gemini-3.1-flash-lite-previewGoogleProprietary$0.25326368 291 · 864,211
134nvidia-nemotron-3.5-super-vl-120b-a12b-nvfp4NVIDIAOpenMDW-1.1–326326 –2,523
135o3-2025-04-16 OpenAIProprietary–326364 293 · 1158,908
136minimax-m2.7MiniMaxModified MIT$0.30324324 –84,977
137deepseek-v3.1-terminusDeepSeekMIT–323323 –3,608
138amazon-nova-experimental-chat-26-01-10AmazonProprietary–319319 –3,539
139deepseek-v3.1DeepSeekMIT$0.25318328 308 · 914,610
140mistral-medium-3.5MistralModified MIT$1.50318351 266 · 211,778
141deepseek-v3.1-thinkingDeepSeekMIT$0.25316326 308 · 911,459
142grok-3-preview-02-24 xAIProprietary–316316 –32,499
143grok-4-0709 xAIProprietary–315315 –39,693
144gpt-5.4-nano-high OpenAIProprietary$0.20315296 336 · 1062,396
145claude-opus-4-20250514 AnthropicProprietary–312322 301 · 643,043
146hunyuan-hy3-previewTencenttencent-hunyuan-community–311311 –6,879
147qwen3.5-35b-a3bAlibabaApache 2.0$0.14311283 344 · 2230,457
148glm-4.5 Z.aiMIT–311315 306 · 623,796
149mistral-medium-2508MistralProprietary–309309 –95,321
150mimo-v2-flash (non-thinking)XiaomiMIT–308279 344 · 748,088
151grok-4-fast-reasoning xAIProprietary$0.20304304 –18,269
152mimo-v2-flash (thinking)XiaomiMIT–303270 344 · 711,142
153gpt-5-mini-high OpenAIProprietary$0.25301276 331 · 526,804
154gemini-2.5-flash-preview-09-2025GoogleProprietary–299299 –32,995
155qwen3-235b-a22b-no-thinkingAlibabaApache 2.0–297297 –37,484
156claude-sonnet-4-20250514-thinking-32k AnthropicProprietary–297297 –34,132
157claude-haiku-4-5-20251001 AnthropicProprietary$1.00294322 270 · 9149,199
158deepseek-r1DeepSeekMIT–290290 –18,524
159qwen3.5-flashAlibabaProprietary–286286 –61,802
160grok-3-mini-high xAIProprietary–286238 355 · 315,596
161hunyuan-vision-1.5-thinkingTencentProprietary–282282 –2,170
161qwen3-235b-a22b-thinking-2507AlibabaApache 2.0–282293 273 · 168,823
162amazon-nova-experimental-chat-12-10AmazonProprietary–281281 –3,733
163qwen3-235b-a22b-instruct-2507AlibabaApache 2.0$0.09281340 237 · 1498,134
164o4-mini-2025-04-16 OpenAIProprietary–278278 –44,855
165minimax-m2.5MiniMaxMIT$0.30277277 –42,815
166qwen3-vl-235b-a22b-thinkingAlibabaApache 2.0–276284 269 · 127,859
167qwen3-coder-480b-a35b-instructAlibabaApache 2.0$0.30274272 277 · 225,195
168claude-3-7-sonnet-20250219-thinking-32k AnthropicProprietary–273273 –38,159
169o1-2024-12-17 OpenAIProprietary–273298 252 · 1127,807
170mistral-medium-2505MistralProprietary–272272 –32,782
171hunyuan-t1-20250711TencentProprietary–271271 –4,595
172qwen3-vl-235b-a22b-instructAlibabaApache 2.0$0.20270320 232 · 1311,320
173gemini-2.5-flashGoogleProprietary$0.30270312 237 · 8125,521
174gpt-oss-120b OpenAIApache 2.0$0.04268224 332 · 430,206
175minimax-m2.1-previewMiniMaxMIT–267267 –17,239
176glm-4.5-air Z.aiMIT–266250 283 · 630,660
177hunyuan-turbos-20250416TencentProprietary–265265 –10,626
178longcat-flash-chatMeituanMIT–264295 239 · 811,168
179qwen3-30b-a3b-instruct-2507AlibabaApache 2.0–264264 –23,322
180qwen3-32bAlibabaApache 2.0$0.08263219 329 · 53,926
181claude-sonnet-4-20250514 AnthropicProprietary–263278 249 · 539,163
182glm-4.7-flash Z.aiMIT–262239 289 · 312,021
183gemini-2.5-flash-lite-preview-09-2025-no-thinkingGoogleProprietary–259259 –47,437
184trinity-large-previewUnknownApache 2.0–258258 –31,266
185glm-4.6v Z.aiMIT–258258 –2,837
186gemini-2.5-flash-lite-preview-06-17-thinkingGoogleProprietary–253253 –32,381
187qwen2.5-maxAlibabaProprietary–251251 –32,487
188granite-4.2-30bIBMApache 2.0$0.16248212 298 · 63,401
189claude-3-7-sonnet-20250219 AnthropicProprietary–248250 245 · 842,572
190mercury-2 InceptionProprietary$0.25246215 288 · 43,197
191qwen3-next-80b-a3b-thinkingAlibabaApache 2.0–246245 247 · 1513,474
192nova-2-liteAmazonProprietary$0.30246207 302 · 712,413
193gpt-4.1-2025-04-14 OpenAIProprietary$2.00245323 197 · 1450,312
194minimax-m2MiniMaxApache 2.0$0.30244215 283 · 56,856
195trinity-large-thinkingUnknownApache 2.0–243243 –30,337
196gpt-oss-20b OpenAIApache 2.0$0.03242192 327 · 410,419
197deepseek-v3-0324DeepSeekMIT$0.24242285 210 · 344,973
198o1-preview OpenAIProprietary–242274 216 · 631,122
199o3-mini-high OpenAIProprietary–240238 242 · 1418,589
200qwen3-next-80b-a3b-instructAlibabaApache 2.0$0.09239291 203 · 1622,760
201minimax-m1MiniMaxApache 2.0–238238 –34,303
202amazon-nova-experimental-chat-11-10AmazonProprietary–238238 –26,039
203mistral-large-3MistralApache 2.0$0.50235322 185 · 384,205
204nvidia-nemotron-3-super-120b-a12bNVIDIANVIDIA Open Model–234234 –7,878
205claude-3-5-sonnet-20241022 AnthropicProprietary–233252 217 · 887,769
206gemini-2.0-flash-001GoogleProprietary–233233 –43,446
207gpt-5-nano-high OpenAIProprietary–233210 262 · 58,132
208qwen3-235b-a22bAlibabaApache 2.0–232253 214 · 1425,948
209grok-3-mini-beta xAIProprietary–231231 –20,931
210o3-mini OpenAIProprietary–231220 242 · 1456,741
211llama-3.1-nemotron-ultra-253b-v1NVIDIANvidia Open Model–230219 243 · 42,549
212mistral-small-2506MistralApache 2.0–229229 –17,462
213intellect-3Prime IntellectMIT–229229 –5,431
214command-a-03-2025CohereCC-BY-NC-4.0–226226 –55,766
215gemini-2.0-flash-lite-preview-02-05GoogleProprietary–226226 –24,955
216glm-4.5v Z.aiMIT–224224 –4,821
217gemini-1.5-pro-002GoogleProprietary–224224 –55,606
217nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4NVIDIAOpenMDW-1.1–224224 –19,938
218step-3StepfunApache 2.0–221221 –6,293
219hunyuan-turbos-20250226TencentProprietary–221221 –2,220
220gpt-4.1-mini-2025-04-14 OpenAIProprietary$0.40220265 189 · 1438,709
221amazon-nova-experimental-chat-10-20AmazonProprietary–220220 –11,626
222amazon-nova-experimental-chat-10-09AmazonProprietary–218218 –2,781
223qwen-plus-0125AlibabaProprietary–218218 –5,819
224qwen3-30b-a3bAlibabaApache 2.0$0.10216200 236 · 626,157
225ling-flash-2.0Ant-groupMIT–215215 –6,947
226nvidia-llama-3.3-nemotron-super-49b-v1.5NVIDIANvidia Open–215215 –3,328
227glm-4-plus-0111 Z.aiProprietary–214214 –5,760
228hunyuan-turbo-0110TencentProprietary–212212 –2,290
229claude-3-5-sonnet-20240620 AnthropicProprietary–210215 205 · 682,419
230granite-4.2-8bIBMApache 2.0$0.06209173 267 · 63,254
230qwq-32bAlibabaApache 2.0–209208 211 · 525,178
231deepseek-v3DeepSeekDeepSeek$0.32209232 191 · 921,770
232gemini-advanced-0514GoogleProprietary–208208 –50,148
233grok-2-2024-08-13 xAIProprietary–208208 –63,498
234gemma-3-27b-itGoogleGemma$0.08207240 183 · 1246,666
234llama-3.1-405b-instruct-bf16MetaLlama 3.1 Community–207207 –41,375
235gpt-4o-2024-05-13 OpenAIProprietary$2.50207218 196 · 4112,881
236llama-3.1-405b-instruct-fp8MetaLlama 3.1 Community–206206 –59,656
237step-2-16k-exp-202412StepfunProprietary–206206 –4,833
238o1-mini OpenAIProprietary–205209 197 · 251,981
239olmo-3.1-32b-instructAi2Apache 2.0–202202 –11,817
240yi-lightning01 AIProprietary–201201 –27,332
241llama-3.3-nemotron-49b-super-v1NVIDIANvidia–200200 –2,218
242llama-4-maverick-17b-128e-instructMetaLlama 4–200200 –39,450
243hunyuan-large-2025-02-10TencentProprietary–199199 –3,738
244gemini-1.5-pro-001GoogleProprietary–197197 –79,138
245deepseek-v2.5-1210DeepSeekDeepSeek–197197 –6,795
246llama-3.3-70b-instructMetaLlama-3.3$0.10196192 200 · 454,497
247ring-flash-2.0Ant-groupMIT–196196 –6,990
248molmo-2-8bAi2Apache 2.0–196196 –822
249llama-4-scout-17b-16e-instructMetaLlama–195195 –29,826
250gpt-4o-2024-08-06 OpenAIProprietary$2.50194208 183 · 1645,499
251granite-4.2-3bIBMApache 2.0$0.03194172 224 · 63,251
252step-1o-turbo-202506StepfunProprietary–194194 –8,901
253glm-4-plus Z.aiProprietary–193193 –26,126
254claude-3-opus-20240229 AnthropicProprietary–193196 190 · 8194,909
255qwen-max-0919AlibabaQwen–192192 –16,478
256gpt-4-turbo-2024-04-09 OpenAIProprietary$10.00192198 187 · 498,114
257qwen2.5-plus-1127AlibabaProprietary–190190 –10,187
258mistral-large-2407MistralMistral Research–190190 –45,459
259athene-v2-chatNexusFlowNexusFlow–189189 –24,739
260nvidia-nemotron-3-nano-30b-a3b-bf16NVIDIANVIDIA Open Model–189189 –15,770
261gpt-4-0125-preview OpenAIProprietary–189189 –93,439
262gpt-4-1106-preview OpenAIProprietary–188188 –100,105
263deepseek-v2.5DeepSeekDeepSeek–187184 191 · 524,572
264hunyuan-standard-2025-02-10TencentProprietary–187187 –3,904
265qwen2.5-72b-instructAlibabaQwen$0.36187181 193 · 1039,406
266gemini-1.5-flash-002GoogleProprietary–186186 –34,902
267grok-2-mini-2024-08-13 xAIProprietary–185185 –52,567
268gemma-3-12b-itGoogleGemma$0.05185214 164 · 113,829
269athene-70b-0725NexusFlowCC-BY-NC-4.0–184184 –19,621
270olmo-3-32b-thinkAi2Apache 2.0–183183 –5,831
271mistral-large-2411MistralMRL–183183 –28,073
272mercury InceptionProprietary–183183 –1,965
273magistral-medium-2506MistralProprietary–183183 –11,510
274granite-4.1-8bIBMApache 2.0–182182 –4,180
275claude-3-5-haiku-20241022 AnthropicProprietary–181198 167 · 669,061
276gpt-4o-mini-2024-07-18 OpenAIProprietary–180192 170 · 468,705
277llama-3.1-70b-instructMetaLlama 3.1 Community$0.40179175 183 · 455,240
278mistral-small-24b-instruct-2501MistralApache 2.0$0.05176164 190 · 514,681
279hunyuan-large-visionTencentProprietary–175175 –5,279
280mistral-small-3.1-24b-instruct-2503MistralApache 2.0–173181 165 · 532,727
281amazon-nova-pro-v1.0AmazonProprietary–173173 –24,745
282reka-core-20240904Reka AIProprietary–171171 –7,312
283gpt-4-0314 OpenAIProprietary–171171 –54,173
284ibm-granite-h-smallIBMApache 2.0–171171 –5,630
285llama-3.1-nemotron-51b-instructNVIDIALlama 3.1–171171 –3,749
286gemini-1.5-flash-001GoogleProprietary–171171 –62,833
286olmo-3.1-32b-thinkAi2Apache 2.0–171171 –8,301
287llama-3.1-tulu-3-70bAi2Llama 3.1–170170 –2,846
288gemma-2-9b-it-simpoPrincetonMIT–167167 –10,072
289jamba-1.5-largeAI21 LabsJamba Open–166172 161 · 48,662
290nemotron-4-340b-instructNVIDIANVIDIA Open Model–165165 –19,659
291llama-3-70b-instructMetaLlama 3 Community–165165 –156,876
292command-r-plus-08-2024CohereCC-BY-NC-4.0–165165 –9,866
293claude-3-sonnet-20240229 AnthropicProprietary–164167 160 · 8109,284
294glm-4-0520 Z.aiProprietary–163163 –9,788
295llama-3.1-nemotron-70b-instructNVIDIALlama 3.1–162178 149 · 57,140
295reka-flash-20240904Reka AIProprietary–162162 –7,536
296gpt-4-0613 OpenAIProprietary–160165 156 · 688,723
297c4ai-aya-expanse-32bCohereCC-BY-NC-4.0–160160 –27,124
298gpt-4.1-nano-2025-04-14 OpenAIProprietary$0.10159196 134 · 116,103
299deepseek-coder-v2DeepSeekDeepSeek License–159159 –15,147
300gemma-3-4b-itGoogleGemma$0.05158181 140 · 114,171
301command-r-plusCohereCC-BY-NC-4.0–157157 –77,554
302amazon-nova-lite-v1.0AmazonProprietary–156156 –19,372
302phi-4MicrosoftMIT$0.07156154 158 · 824,126
303gemini-1.5-flash-8b-001GoogleProprietary–155155 –35,558
304qwen2-72b-instructAlibabaQianwen LICENSE–155157 154 · 1037,325
305qwen2.5-coder-32b-instructAlibabaApache 2.0–153161 146 · 75,432
306olmo-2-0325-32b-instructAi2Apache-2.0–152152 –3,334
307command-r-08-2024CohereCC-BY-NC-4.0–151151 –10,140
308gemma-2-27b-itGoogleGemma license–151172 134 · 875,754
309claude-3-haiku-20240307 AnthropicProprietary–150157 145 · 8117,701
310mistral-large-2402MistralProprietary–148148 –62,436
311amazon-nova-micro-v1.0AmazonProprietary–147147 –19,364
312ministral-8b-2410MistralMRL–146146 –4,781
313gemma-3n-e4b-itGoogleGemma–145192 116 · 822,137
314gemini-pro-dev-apiGoogleProprietary–145145 –18,354
315qwq-32b-previewAlibabaApache 2.0–145116 191 · 33,231
316qwen1.5-110b-chatAlibabaQianwen LICENSE–144144 –26,195
317qwen1.5-72b-chatAlibabaQianwen LICENSE–144144 –39,302
317reka-flash-21b-20240226-onlineReka AIProprietary–144144 –15,450
318hunyuan-standard-256kTencentProprietary–144144 –2,728
319jamba-1.5-miniAI21 LabsJamba Open–143147 139 · 48,858
320mixtral-8x22b-instruct-v0.1MistralApache 2.0–142142 –51,416
321gemma-2-9b-itGoogleGemma license–142160 127 · 854,611
322reka-flash-21b-20240226Reka AIProprietary–141141 –24,806
323gemini-proGoogleProprietary–140140 –6,390
323llama-3-8b-instructMetaLlama 3 Community–140140 –104,642
324command-rCohereCC-BY-NC-4.0–140141 138 · 454,036
325c4ai-aya-expanse-8bCohereCC-BY-NC-4.0–140140 –9,818
326mistral-mediumMistralProprietary–139139 –34,550
327llama-3.1-tulu-3-8bAi2Llama 3.1–139139 –2,896
328llama-3.1-8b-instructMetaLlama 3.1 Community$0.02138135 140 · 449,605
329gpt-3.5-turbo-0125 OpenAIProprietary$0.50136141 132 · 466,207
330zephyr-orpo-141b-A35b-v0.1HuggingFaceApache 2.0–136136 –4,652
331yi-1.5-34b-chat01 AIApache-2.0–136136 –24,146
332granite-3.1-8b-instructIBMApache 2.0–134134 –3,090
333gpt-3.5-turbo-1106 OpenAIProprietary–132132 –16,619
334qwen1.5-32b-chatAlibabaQianwen LICENSE–132132 –21,741
335gemma-2-2b-itGoogleGemma license–131131 –46,616
336phi-3-medium-4k-instructMicrosoftMIT–130130 –25,055
337mixtral-8x7b-instruct-v0.1MistralApache 2.0–130130 –73,503
338dbrx-instruct-previewDatabricksDBRX LICENSE–129129 –32,191
339qwen1.5-14b-chatAlibabaQianwen LICENSE–128128 –17,839
340internlm2_5-20b-chatInternLMOther–128128 –9,901
341deepseek-llm-67b-chatDeepSeekDeepSeek License–126126 –4,932
342wizardlm-70bMicrosoftLlama 2 Community–125125 –8,214
343yi-34b-chat01 AIYi License–125125 –15,483
344granite-3.0-8b-instructIBMApache 2.0–125125 –6,638
344openchat-3.5OpenChatApache-2.0–125125 –7,968
345llama-3.2-3b-instructMetaLlama 3.2–125120 130 · 77,936
346gemma-1.1-7b-itGoogleGemma license–125125 –23,893
346openchat-3.5-0106OpenChatApache-2.0–125125 –12,637
347snowflake-arctic-instructSnowflakeApache 2.0–124124 –32,832
348granite-3.1-2b-instructIBMApache 2.0–123123 –3,188
349tulu-2-dpo-70bAllenAI/UWAI2 ImpACT Low-risk–123123 –6,535
350openhermes-2.5-mistral-7b Nous ResearchApache-2.0–123123 –5,006
351vicuna-33bLMSYSNon-commercial–122122 –22,479
352phi-3-small-8k-instructMicrosoftMIT–121121 –17,766
353starling-lm-7b-betaNexusflowApache-2.0–121121 –16,056
354llama-2-70b-chatMetaLlama 2 Community–121121 –38,492
355starling-lm-7b-alphaUC BerkeleyCC-BY-NC-4.0–120120 –10,224
356nous-hermes-2-mixtral-8x7b-dpo Nous ResearchApache-2.0–119119 –3,777
357granite-3.0-2b-instructIBMApache 2.0–116116 –6,837
358llama2-70b-steerlm-chatNVIDIALlama 2 Community–116116 –3,585
359solar-10.7b-instruct-v1.0Upstage AICC-BY-NC-4.0–115115 –4,155
360dolphin-2.2.1-mistral-7bCognitive ComputationsApache-2.0–115115 –1,679
361mpt-30b-chatMosaicMLCC-BY-NC-SA-4.0–115115 –2,572
362mistral-7b-instruct-v0.2MistralApache-2.0–114114 –19,402
362wizardlm-13bMicrosoftLlama 2 Community–114114 –7,044
363falcon-180b-chatTIIFalcon-180B TII License–114114 –1,295
364qwen1.5-7b-chatAlibabaQianwen LICENSE–112112 –4,737
365phi-3-mini-4k-instruct-june-2024MicrosoftMIT–112112 –12,297
366vicuna-13bLMSYSLlama 2 Community–112112 –19,367
367llama-2-13b-chatMetaLlama 2 Community–112112 –19,174
368palm-2GoogleProprietary–111111 –8,554
368qwen-14b-chatAlibabaQianwen LICENSE–111111 –4,964
369gemma-7b-itGoogleGemma license–111111 –8,925
370codellama-34b-instructMetaLlama 2 Community–110110 –7,366
371zephyr-7b-betaHuggingFaceMIT–109109 –11,118
372phi-3-mini-128k-instructMicrosoftMIT–108108 –20,685
373phi-3-mini-4k-instructMicrosoftMIT–108108 –20,118
374guanaco-33bUWNon-commercial–108108 –2,921
375zephyr-7b-alphaHuggingFaceMIT–107107 –1,785
376stripedhyena-nous-7bTogether AIApache 2.0–106106 –5,182
377codellama-70b-instructMetaLlama 2 Community–105105 –1,143
378gemma-1.1-2b-itGoogleGemma license–105105 –10,854
379vicuna-7bLMSYSLlama 2 Community–104104 –6,923
380smollm2-1.7b-instructHuggingFaceApache 2.0–104104 –2,199
381llama-3.2-1b-instructMetaLlama 3.2–103103 –8,045
382mistral-7b-instructMistralApache 2.0–103103 –8,977
383llama-2-7b-chatMetaLlama 2 Community–102102 –14,148
384gemma-2b-itGoogleGemma license–9898 –4,780
385qwen1.5-4b-chatAlibabaQianwen LICENSE–9898 –7,597
386olmo-7b-instructAi2Apache-2.0–9393 –6,328
387koala-13bUC BerkeleyNon-commercial–9292 –6,965
388alpaca-13bStanfordNon-commercial–9292 –5,745
389gpt4all-13b-snoozyNomic AINon-commercial–9191 –1,743
390mpt-7b-chatMosaicMLCC-BY-NC-SA-4.0–9090 –3,924
391chatglm3-6bTsinghuaApache-2.0–8989 –4,658
392RWKV-4-Raven-14BRWKVApache 2.0–8585 –4,845
393chatglm2-6bTsinghuaApache-2.0–8181 –2,658
394oasst-pythia-12bOpenAssistantApache 2.0–8181 –6,310
395chatglm-6bTsinghuaNon-commercial–7474 –4,914
396fastchat-t5-3bLMSYSApache 2.0–7373 –4,203
397dolly-v2-12bDatabricksMIT–7171 –3,412
398llama-13bMetaNon-commercial–7070 –2,391
399stablelm-tuned-alpha-7bStability AICC-BY-NC-SA-4.0–6565 –3,287

Leaders by task

The top model for each kind of task, scored from votes on that task alone, and how many models were ranked.

TaskLeaderScoreModels ranked
Business and finance Gemini 4 Argon (High) 689409
Chinese Gemini 4 Argon (High) 857392
Coding Gemini 4 Argon (High) 803411
Creative writing Claude Opus 5.5 (High) 682414
English Gemini 4 Argon (High) 726416
Entertainment and media Gemini 4 Argon (High) 676414
Expert Claude Fable 5 (High) 781366
French Muse Spark 1.3 (Max) 714297
German Muse Spark 1.3 (Max) 703314
Hard prompts Gemini 4 Argon (High) 777416
Hard prompts in English Gemini 4 Argon (High) 783414
Instruction following Gemini 4 Argon (High) 710416
Japanese Claude Fable 5.1 (Max) 781280
Korean Claude Fable 5.1 (Max) 614284
Law and government Gemini 4 Argon (High) 740388
Long prompts Gemini 4 Argon (High) 760394
Math Gemini 4 Argon (High) 716400
Maths work Gemini 4 Argon (High) 770398
Medicine and health Gemini 4 Argon (High) 783386
Multi-turn conversations Gemini 4 Argon (High) 786414
Non-English prompts Gemini 4 Argon (High) 651416
Polish Claude Fable 5.1 (Max) 660236
Russian Muse Wonder (Max) 724380
Science Gemini 4 Argon (High) 748414
Software and IT Gemini 4 Argon (High) 809416
Spanish Claude Opus 5.5 (High) 620301
Writing and literature Claude Opus 5.5 (High) 692415

Fixed tests with right and wrong answers, scored out of 100%.

GPQA

Graduate-level science questions written to be hard to look up. · Top 10 of 256 · Higher is better

MMLU-Pro

Broad knowledge and reasoning across 14 subjects, ten answer choices each. · Top 10 of 142 · Higher is better

AIME 2025

Competition maths problems from the 2025 American Invitational Mathematics Exam. · Top 10 of 123 · Higher is better