M
MODELYST
AI research terminal
●
live · verified Jul 27
Search
⌘K
Frontier
Models
Compare
Leaderboards
Changes
Media
Benchmarks
Papers
Pick
Discover
Ask
Frontier
Models
Compare
Leaderboards
Changes
Media
Benchmarks
Papers
Pick
Discover
Ask
Leaderboards
/
AA Long-Context Reasoning Leaderboard
LDR
AA Long-Context Reasoning Leaderboard
AA Long-Context Reasoning
☆ Watch
1
GPT-5.2 Codex
Jul 27, 2026
75.7
2
GPT-5
Jul 27, 2026
75.6
3
GPT-5.1
Jul 27, 2026
75
4
Kimi K3
Jul 27, 2026
74.7
5
GPT-5.5
Jul 27, 2026
74.3
6
Claude Opus 4.5
Jul 27, 2026
74
7
GPT-5.4
Jul 27, 2026
74
8
KAT-Coder-Pro V1
Jul 27, 2026
74
9
MiniMax-M3
Jul 27, 2026
74
10
GPT-5.3 Codex
Jul 27, 2026
74
11
GPT-5.6 Luna (max)
Jul 27, 2026
74
12
GPT-5.6 Terra (max)
Jul 27, 2026
74
13
GPT-5.6 Sol (max)
Jul 27, 2026
73.7
14
MiMo-V2.5-Pro
Jul 27, 2026
73.3
15
GPT-5.2
Jul 27, 2026
72.7
16
Gemini 3.1 Pro Preview
Jul 27, 2026
72.7
17
GLM-5.2 (max)
Jul 27, 2026
71.3
18
GPT-5.6 Terra
Jul 27, 2026
71.3
19
GPT-5.6 Sol
Jul 27, 2026
71
20
Claude Opus 4.6
Jul 27, 2026
70.7
21
Gemini 3 Pro Preview
Jul 27, 2026
70.7
22
Claude Sonnet 4.6
Jul 27, 2026
70.7
23
Claude Sonnet 5
Jul 27, 2026
70.7
24
Claude Opus 4.7
Jul 27, 2026
70.3
25
Claude 4.5 Haiku
Jul 27, 2026
70.3
26
Claude Opus 5
Jul 27, 2026
70
27
Claude Fable 5
Jul 27, 2026
70
28
Qwen3.6 Max Preview
Jul 27, 2026
69.7
29
Qwen3.6 Plus
Jul 27, 2026
69.7
30
Kimi K2.6
Jul 27, 2026
69.7
31
Gemini 3.6 Flash
Jul 27, 2026
69.7
32
Muse Spark
Jul 27, 2026
69.7
33
GPT-5.6 Luna
Jul 27, 2026
69.7
34
GPT-5.4 mini
Jul 27, 2026
69.3
35
Gemini 3.5 Flash
Jul 27, 2026
69.3
36
o3
Jul 27, 2026
69.3
37
DeepSeek V3.2 Exp
Jul 27, 2026
69
38
GPT-5 Codex
Jul 27, 2026
69
39
Qwen3.7 Max
Jul 27, 2026
69
40
MiniMax-M2.7
Jul 27, 2026
68.7
41
Qwen3.6 27B
Jul 27, 2026
68.7
42
Grok 4
Jul 27, 2026
68
43
Grok 4.1 Fast
Jul 27, 2026
68
44
Nex-N2-Pro
Jul 27, 2026
67.7
45
Grok 4.5
Jul 27, 2026
67.7
46
Claude Opus 4.8
Jul 27, 2026
67.7
47
Qwen3.5 27B
Jul 27, 2026
67.3
48
GPT-5.1 Codex
Jul 27, 2026
67.3
49
Qwen3 235B A22B 2507
Jul 27, 2026
67
50
Nemotron 3 Ultra 550B A55B
Jul 27, 2026
67
51
Qwen3.5 122B A10B
Jul 27, 2026
66.7
52
Hy3
Jul 27, 2026
66.7
53
MiMo-V2-Omni
Jul 27, 2026
66.7
54
Kimi K2 Thinking
Jul 27, 2026
66.3
55
Claude 4.1 Opus
Jul 27, 2026
66.3
56
Gemini 3 Flash Preview
Jul 27, 2026
66.3
57
Kimi K2.7 Code
Jul 27, 2026
66.3
58
DeepSeek V4 Pro
Jul 27, 2026
66.3
59
Qwen3 Max Thinking
Jul 27, 2026
66
60
MiniMax-M2.5
Jul 27, 2026
66
61
GPT-5 mini
Jul 27, 2026
66
62
GPT-5.4 nano
Jul 27, 2026
66
63
KAT Coder Pro V2
Jul 27, 2026
66
64
Gemini 2.5 Pro
Jul 27, 2026
66
65
Claude 4.5 Sonnet
Jul 27, 2026
65.7
66
Qwen3.5 397B A17B
Jul 27, 2026
65.7
67
Kimi K2.5
Jul 27, 2026
65.3
68
Doubao Seed Code
Jul 27, 2026
65.3
69
Gemini 3.1 Flash-Lite
Jul 27, 2026
65.3
70
DeepSeek V3.2
Jul 27, 2026
65
71
DeepSeek V3.1 Terminus
Jul 27, 2026
65
72
Qwen3.7 Plus
Jul 27, 2026
65
73
Grok Build 0.1 0616
Jul 27, 2026
64.7
74
Grok 4 Fast
Jul 27, 2026
64.7
75
Claude 4 Sonnet
Jul 27, 2026
64.7
76
Gemini 2.5 Flash Preview (Sep '25)
Jul 27, 2026
64.3
77
Ring-2.6-1T
Jul 27, 2026
64.3
78
MiMo-V2-Flash (Feb 2026)
Jul 27, 2026
64.3
79
Grok 4.3
Jul 27, 2026
64.3
80
GLM-4.7
Jul 27, 2026
64
81
GPT-5.5 Instant (May 2026)
Jul 27, 2026
64
82
GPT-5 (ChatGPT)
Jul 27, 2026
63.7
83
Agnes 2.5 Pro Alpha
Jul 27, 2026
63.7
84
Qwen3.6 35B A3B
Jul 27, 2026
63.7
85
MiMo-V2-Omni-0327
Jul 27, 2026
63.7
86
Step 3.7 Flash
Jul 27, 2026
63.7
87
GLM-5
Jul 27, 2026
63.3
88
Inkling
Jul 27, 2026
63.3
89
Muse Spark 1.1
Jul 27, 2026
63.3
90
MiMo-V2-Flash
Jul 27, 2026
63
91
DeepSeek V4 Flash
Jul 27, 2026
63
92
GPT-5.1 Codex mini
Jul 27, 2026
62.7
93
Qwen3.5 35B A3B
Jul 27, 2026
62.7
94
MiMo-V2.5
Jul 27, 2026
62.7
95
GLM-5.1
Jul 27, 2026
62.3
96
Gemini 3.5 Flash-Lite
Jul 27, 2026
62
97
Gemma 4 31B
Jul 27, 2026
62
98
Gemini 2.5 Flash
Jul 27, 2026
61.7
99
Motif 3 (Beta)
Jul 27, 2026
61.3
100
GLM 5V Turbo
Jul 27, 2026
61
101
MiniMax-M2
Jul 27, 2026
61
102
GPT-4.1
Jul 27, 2026
61
103
Mistral Medium 3.5
Jul 27, 2026
61
104
GLM-5-Turbo
Jul 27, 2026
60.7
105
MiMo-V2-Pro
Jul 27, 2026
60.7
106
Claude 3.7 Sonnet
Jul 27, 2026
60.7
107
Qwen3 Next 80B A3B
Jul 27, 2026
60.3
108
NVIDIA Nemotron 3 Super 120B A12B
Jul 27, 2026
60
109
DeepSeek V3.2 Speciale
Jul 27, 2026
59.3
110
o1
Jul 27, 2026
59.3
111
Qwen3 30B A3B 2507
Jul 27, 2026
59
112
MiniMax-M2.1
Jul 27, 2026
59
113
Grok 4.20 0309
Jul 27, 2026
59
114
Gemini 2.5 Flash-Lite Preview (Sep '25)
Jul 27, 2026
59
115
Qwen3.5 9B
Jul 27, 2026
59
116
Qwen3 VL 235B A22B
Jul 27, 2026
58.7
117
JT-4.1 Flash 236B A21B
Jul 27, 2026
58.7
118
Nova 2.0 Lite
Jul 27, 2026
58.3
119
Grok 4.20 0309 v2
Jul 27, 2026
58
120
LongCat 2.0
Jul 27, 2026
58
121
Seed-OSS-36B-Instruct
Jul 27, 2026
57.7
122
Qwen3 Max Thinking (Preview)
Jul 27, 2026
57.7
123
GPT-5.5 Instant (May 2026)
Jul 27, 2026
55.7
124
Qwen3.5 4B
Jul 27, 2026
55.7
125
K-EXAONE
Jul 27, 2026
55.7
126
Gemma 4 26B A4B
Jul 27, 2026
55.7
127
Qwen3 VL 32B
Jul 27, 2026
55.3
128
JT-35B-Flash
Jul 27, 2026
55.3
129
Gemma 4 12B
Jul 27, 2026
55.3
130
o4-mini
Jul 27, 2026
55
131
Grok 3
Jul 27, 2026
54.7
132
DeepSeek R1 0528 (May '25)
Jul 27, 2026
54.7
133
Hy3-preview
Jul 27, 2026
54.7
134
GLM-4.6
Jul 27, 2026
54.3
135
MiniMax M1 80k
Jul 27, 2026
54.3
136
Step 3.5 Flash 2603
Jul 27, 2026
54.3
137
Nova 2.0 Pro Preview
Jul 27, 2026
54.3
138
Nova 2.0 Omni
Jul 27, 2026
53.7
139
GPT-4o (ChatGPT)
Jul 27, 2026
53
140
Qwen3.5 Omni Plus
Jul 27, 2026
52.7
141
K2 Think V2
Jul 27, 2026
52.7
142
Kimi K2 0905
Jul 27, 2026
52.3
143
DeepSeek R1 (Jan '25)
Jul 27, 2026
52.3
144
MiniMax M1 40k
Jul 27, 2026
51.7
145
Gemini 2.5 Flash-Lite
Jul 27, 2026
51.3
146
Qwen3 Next 80B A3B Instruct
Jul 27, 2026
51.3
147
Magistral Medium 1.2
Jul 27, 2026
51.3
148
Kimi K2
Jul 27, 2026
51
149
gpt-oss-120b
Jul 27, 2026
50.7
150
Grok 3 mini Reasoning
Jul 27, 2026
50.3
151
Apriel-v1.6-15B-Thinker
Jul 27, 2026
50.3
152
EXAONE 4.5 33B
Jul 27, 2026
49.3
153
GLM-4.5
Jul 27, 2026
48.3
154
Grok Code Fast 1
Jul 27, 2026
48.3
155
Qwen3 Max
Jul 27, 2026
46.7
156
Command A+
Jul 27, 2026
46
157
Llama 4 Maverick
Jul 27, 2026
46
158
Ring-1T
Jul 27, 2026
45.7
159
DeepSeek V3.1
Jul 27, 2026
45
160
Mistral Small 4
Jul 27, 2026
44.7
161
Qwen3.5 Omni Flash
Jul 27, 2026
44
162
GLM-4.5-Air
Jul 27, 2026
43.7
163
Step 3.5 Flash
Jul 27, 2026
43
164
Qwen3 Coder 480B A35B Instruct
Jul 27, 2026
42.3
165
GPT-4.1 mini
Jul 27, 2026
42.3
166
GPT-5 nano
Jul 27, 2026
41.7
167
DeepSeek V3 0324
Jul 27, 2026
41
168
Qwen3 VL 30B A3B
Jul 27, 2026
40.7
169
GLM-4.6V
Jul 27, 2026
40.3
170
Qwen3 Coder Next
Jul 27, 2026
40
171
NVIDIA Nemotron Nano 12B v2 VL
Jul 27, 2026
40
172
Qwen3 Max (Preview)
Jul 27, 2026
39.7
173
Qwen3 4B 2507
Jul 27, 2026
37.7
174
GLM-5.2
Jul 27, 2026
37.3
175
Mercury 2
Jul 27, 2026
36.3
176
Solar Open 100B
Jul 27, 2026
36
177
Nemotron 3 Nano Omni 30B A3B Reasoning
Jul 27, 2026
35.7
178
GLM-4.7-Flash
Jul 27, 2026
35
179
GPT-4o
Jul 27, 2026
35
180
Ling-1T
Jul 27, 2026
34.7
181
Ling-2.6-1T
Jul 27, 2026
34.7
182
G9v3-3B
Jul 27, 2026
34.7
183
Mistral Large 3
Jul 27, 2026
34.7
184
Nemotron Cascade 2 30B A3B
Jul 27, 2026
34
185
Llama Nemotron Super 49B v1.5
Jul 27, 2026
34
186
Claude 4 Opus
Jul 27, 2026
33.7
187
NVIDIA Nemotron 3 Nano 30B A3B
Jul 27, 2026
33.7
188
K2-V2
Jul 27, 2026
33.3
189
Trinity Large Thinking
Jul 27, 2026
33
190
North Mini Code
Jul 27, 2026
32.3
191
INTELLECT-3
Jul 27, 2026
32.3
192
Qwen3 VL 235B A22B Instruct
Jul 27, 2026
31.7
193
HyperNova 60B 2605
Jul 27, 2026
31.7
194
Qwen3 VL 32B Instruct
Jul 27, 2026
31.3
195
Qwen3 235B A22B 2507 Instruct
Jul 27, 2026
31.2
196
Qwen3 VL 8B
Jul 27, 2026
31
197
Gemma 4 E4B
Jul 27, 2026
30.7
198
gpt-oss-20b
Jul 27, 2026
30.7
199
Nova Premier
Jul 27, 2026
30
200
Devstral 2
Jul 27, 2026
30
201
Qwen3 Coder 30B A3B Instruct
Jul 27, 2026
29
202
DeepSeek V3 (Dec '24)
Jul 27, 2026
29
203
Devstral Medium
Jul 27, 2026
28.7
204
Gemini 2.0 Flash (Feb '25)
Jul 27, 2026
28.3
205
Mistral Medium 3
Jul 27, 2026
28
206
Solar Pro 3
Jul 27, 2026
27
207
Devstral Small (May '25)
Jul 27, 2026
26.7
208
Llama 4 Scout
Jul 27, 2026
25.8
209
LongCat Flash Lite
Jul 27, 2026
25.7
210
Kimi Linear 48B A3B Instruct
Jul 27, 2026
25.7
211
QwQ 32B
Jul 27, 2026
25
212
Ling 2.6 Flash
Jul 27, 2026
25
213
Llama 3.1 Instruct 405B
Jul 27, 2026
24.3
214
Devstral Small 2
Jul 27, 2026
24
215
Ministral 3 8B
Jul 27, 2026
24
216
Qwen3 VL 30B A3B Instruct
Jul 27, 2026
23.7
217
Qwen3.5 2B
Jul 27, 2026
23.7
218
Claude 3.5 Haiku
Jul 27, 2026
23.3
219
Qwen3 30B A3B 2507 Instruct
Jul 27, 2026
22.7
220
Ministral 3 14B
Jul 27, 2026
22
221
Cogito v2.1
Jul 27, 2026
21.7
222
Qwen3 VL 4B
Jul 27, 2026
21.3
223
Claude 3 Haiku
Jul 27, 2026
21
224
Ring-flash-2.0
Jul 27, 2026
21
225
NVIDIA-Nemotron-Nano-9B-v2
Jul 27, 2026
21
226
Hermes 4 - Llama-3.1 405B
Jul 27, 2026
20.7
227
Qwen2.5 Instruct 72B
Jul 27, 2026
20.3
228
Apriel-v1.5-15B-Thinker
Jul 27, 2026
20
229
Mistral Small 3.1
Jul 27, 2026
19.7
230
Mistral Medium 3.1
Jul 27, 2026
19.7
231
Nova Pro
Jul 27, 2026
19
232
Granite 4.1 30B
Jul 27, 2026
18.7
233
Nova Lite
Jul 27, 2026
17.7
234
Mistral Small 3.2
Jul 27, 2026
17.3
235
Jamba 1.7 Large
Jul 27, 2026
17.3
236
Llama-3_3-Nemotron-Super-49B-v1
Jul 27, 2026
17
237
Devstral Small (Jul '25)
Jul 27, 2026
17
238
GPT-4.1 nano
Jul 27, 2026
17
239
NVIDIA Nemotron 3 Nano 4B
Jul 27, 2026
16.7
240
Magistral Small 1.2
Jul 27, 2026
16.3
241
Llama 3.1 Instruct 8B
Jul 27, 2026
15.7
242
Qwen3 VL 8B Instruct
Jul 27, 2026
15.3
243
Ling-flash-2.0
Jul 27, 2026
15
244
Gemma 4 E2B
Jul 27, 2026
15
245
Llama 3.3 Instruct 70B
Jul 27, 2026
15
246
Tri-21B-think Preview
Jul 27, 2026
14.7
247
DiffusionGemma 26B A4B
Jul 27, 2026
14.3
248
EXAONE 4.0 32B
Jul 27, 2026
14
249
Phi-4-mini-instruct
Jul 27, 2026
13.7
250
Qwen3 VL 4B Instruct
Jul 27, 2026
13
251
DeepSeek R1 0528 Qwen3 8B
Jul 27, 2026
13
252
Motif-2-12.7B-Reasoning
Jul 27, 2026
13
253
Jamba 1.7 Mini
Jul 27, 2026
12.7
254
Granite 4.1 8B
Jul 27, 2026
12
255
JT-MINI
Jul 27, 2026
11.7
256
HyperCLOVA X SEED Think (32B)
Jul 27, 2026
11.7
257
Ministral 3 3B
Jul 27, 2026
11.7
258
Llama 3.2 Instruct 11B (Vision)
Jul 27, 2026
11.7
259
DeepSeek R1 Distill Llama 70B
Jul 27, 2026
11
260
Tri-21B-Think
Jul 27, 2026
11
261
Mi:dm K 2.5 Pro Preview
Jul 27, 2026
11
262
Pixtral Large
Jul 27, 2026
10.3
263
DeepSeek R1 Distill Qwen 32B
Jul 27, 2026
9.7
264
Nova Micro
Jul 27, 2026
9.7
265
Mi:dm K 2.5 Pro
Jul 27, 2026
9
266
Granite 4.0 H Small
Jul 27, 2026
9
267
Falcon-H1R-7B
Jul 27, 2026
8.7
268
Qwen3 4B 2507 Instruct
Jul 27, 2026
7.3
269
Llama 3.1 Nemotron Ultra 253B v1
Jul 27, 2026
7.3
270
DeepSeek R1 Distill Qwen 14B
Jul 27, 2026
7
271
Jamba Reasoning 3B
Jul 27, 2026
7
272
Llama 3.1 Nemotron Instruct 70B
Jul 27, 2026
7
273
Gemma 3 12B Instruct
Jul 27, 2026
6.7
274
Ling-mini-2.0
Jul 27, 2026
6.7
275
ERNIE 5.0 Thinking Preview
Jul 27, 2026
6.7
276
Hermes 4 - Llama-3.1 70B
Jul 27, 2026
6.7
277
Llama 3.1 Instruct 70B
Jul 27, 2026
6.3
278
MiniCPM-V 4.6 1.3B
Jul 27, 2026
6.3
279
Granite 4.0 H 1B
Jul 27, 2026
6.3
280
Gemma 3 4B Instruct
Jul 27, 2026
5.7
281
Gemma 3 27B Instruct
Jul 27, 2026
5.7
282
Mistral Large 2 (Nov '24)
Jul 27, 2026
5.3
283
Qwen3.5 0.8B
Jul 27, 2026
5.3
284
Llama 3.2 Instruct 1B
Jul 27, 2026
5
285
Granite 3.3 8B
Jul 27, 2026
4.3
286
Granite 4.0 1B
Jul 27, 2026
4
287
Granite 4.0 Micro
Jul 27, 2026
4
288
MiniCPM5-1B
Jul 27, 2026
3.7
289
Granite 4.1 3B
Jul 27, 2026
3
290
ERNIE 4.5 300B A47B
Jul 27, 2026
2.3
291
Phi-3 Mini Instruct 3.8B
Jul 27, 2026
2
292
Llama 3.2 Instruct 3B
Jul 27, 2026
2
293
Mistral Large 2 (Jul '24)
Jul 27, 2026
1.7
294
DeepSeek R1 Distill Qwen 1.5B
Jul 27, 2026
0.3
295
Qwen3 1.7B
Jul 27, 2026
0
296
Qwen3 0.6B
Jul 27, 2026
0
297
Qwen3 4B
Jul 27, 2026
0
298
Qwen3 8B
Jul 27, 2026
0
299
Qwen3 14B
Jul 27, 2026
0
300
Qwen3 30B A3B
Jul 27, 2026
0
301
Qwen3 32B
Jul 27, 2026
0
302
Qwen3 235B A22B
Jul 27, 2026
0
303
GLM-4.5V
Jul 27, 2026
0
304
Sarvam M
Jul 27, 2026
0
305
Olmo 3 32B Think
Jul 27, 2026
0
306
OLMo 2 7B
Jul 27, 2026
0
307
OLMo 2 32B
Jul 27, 2026
0
308
Llama 3.1 Nemotron Nano 4B v1.1
Jul 27, 2026
0
309
LFM2 1.2B
Jul 27, 2026
0
310
DeepSeek R1 Distill Llama 8B
Jul 27, 2026
0
311
Magistral Small 1
Jul 27, 2026
0
312
Magistral Medium 1
Jul 27, 2026
0
313
Mistral 7B Instruct
Jul 27, 2026
0
314
Mistral Small 3
Jul 27, 2026
0
315
Gemma 3n E4B Instruct
Jul 27, 2026
0
316
Gemma 3 1B Instruct
Jul 27, 2026
0
317
Gemma 3n E2B Instruct
Jul 27, 2026
0
318
Llama 3 Instruct 8B
Jul 27, 2026
0
319
Llama 3 Instruct 70B
Jul 27, 2026
0
320
GPT-4o (Nov '24)
Jul 27, 2026
0
321
Qwen3 Omni 30B A3B
Jul 27, 2026
0
322
Qwen3 Omni 30B A3B Instruct
Jul 27, 2026
0
323
Tiny Aya Global
Jul 27, 2026
0
324
Apertus 8B Instruct
Jul 27, 2026
0
325
Apertus 70B Instruct
Jul 27, 2026
0
326
Nanbeige4.1-3B
Jul 27, 2026
0
327
Sarvam 30B
Jul 27, 2026
0
328
Sarvam 105B
Jul 27, 2026
0
329
Exaone 4.0 1.2B
Jul 27, 2026
0
330
Reka Flash 3
Jul 27, 2026
0
331
Granite 4.0 H 350M
Jul 27, 2026
0
332
Granite 4.0 350M
Jul 27, 2026
0
333
Olmo 3 7B Instruct
Jul 27, 2026
0
334
Olmo 3 7B Think
Jul 27, 2026
0
335
Olmo 3.1 32B Instruct
Jul 27, 2026
0
336
Olmo 3.1 32B Think
Jul 27, 2026
0
337
Molmo2-8B
Jul 27, 2026
0
338
Molmo 7B-D
Jul 27, 2026
0
339
Step3 VL 10B
Jul 27, 2026
0
340
Solar Pro 2
Jul 27, 2026
0
341
LFM2.5-8B-A1B
Jul 27, 2026
0
342
LFM2.5-VL-1.6B
Jul 27, 2026
0
343
LFM2.5-1.2B-Thinking
Jul 27, 2026
0
344
LFM2 24B A2B
Jul 27, 2026
0
345
LFM2 8B A1B
Jul 27, 2026
0
346
LFM2 2.6B
Jul 27, 2026
0
347
LFM2.5-1.2B-Instruct
Jul 27, 2026
0
348
phi-4
Jul 27, 2026
0
349
gemma-3-270m
Jul 27, 2026
0