Skip to content
TrustList
AI Models

AI Model Rankings

Models are ranked by the Artificial Analysis Intelligence Index v5.0.1 wherever it has tested them. Models it has not tested follow, ordered by a blend of public benchmarks, verified reviews and community votes. Every model links to its full profile.

Vote#ModelBlendCapabilityRatingArtificial Analysis Intelligence Index v5.0.1Artificial Analysis Intelligence IndexArtificial Analysis Intelligence Index v4.3.2MMLUMMLU-Pro
1
Google · 1,000,000 ctx · Proprietary
60
+16 vs avg
60-60 index
+23.78
----
2
Anthropic · 1,000,000 ctx · Proprietary
59
+15 vs avg
59-59 index
+22.78
-58 index
+9.6
--
3
OpenAI · 1,050,000 ctx · Proprietary
57
+13 vs avg
57-57 index
+20.78
----
4
Anthropic · 1,000,000 ctx · Proprietary
56
+12 vs avg
56-55 index
+18.78
-56 index
+7.6
--
5
OpenAI · 1,050,000 ctx · Proprietary
54
+10 vs avg
54-55 index
+18.78
-52 index
+3.6
--
6
OpenAI · 1,050,000 ctx · Proprietary
51
+7 vs avg
51-51 index
+14.78
----
7
Google · 1,000,000 ctx · Proprietary
52
+8 vs avg
52-50 index
+13.78
-53 index
+4.6
--
8
Anthropic · 1,000,000 ctx · Proprietary
49
+5 vs avg
49-49 index
+12.78
----
9
Moonshot AI · 3T-class (per Moonshot) params · 1,048,576 ctx · Weights promised by 4 November 2026; licence not yet named
46
+2 vs avg
46-46 index
+9.78
----
10
Meta · 1,048,576 ctx · Proprietary (no licence stated; weights not published)
44
+0 vs avg
44-44 index
+7.78
----
11
Anthropic · 1,000,000 ctx · Proprietary
36
−8 vs avg
36-36 index
−0.22
----
12
xAI · 500,000 ctx · Proprietary
41
−3 vs avg
41-35 index
−1.22
-46 index
−2.4
--
13
Alibaba · 2.4T (95B active) params · 1,000,000 ctx · Proprietary (weights announced)
34
−10 vs avg
34-34 index
−2.22
----
14
Z.ai (Zhipu AI) · 1,000,000 ctx · Proprietary at launch; weights released ~2 weeks later
32
−12 vs avg
32-32 index
−4.22
----
15
Google · Proprietary
31
−13 vs avg
31-31 index
−5.22
----
16
Xiaomi · 1.02T total, 42B active (sparse mixture of experts) params · 1,000,000 ctx · MIT — open weights (published as MiMo-V2.6-Pro-RL)
38
−6 vs avg
38-30 index
−6.22
-46 index
−2.4
--
17
StepFun · 600B total, 27B active per token (sparse mixture of experts) params · 1,000,000 ctx · Proprietary — BF16 open weights announced for 15 October 2026, not published yet
37
−7 vs avg
37-29 index
−7.22
-44 index
−4.4
--
18
MiniMax · Proprietary (weights to be released later, per MiniMax)
29
−15 vs avg
29-29 index
−7.22
----
19
OpenAI · 1,050,000 ctx · Proprietary
33
−11 vs avg
33-28 index
−8.22
-37 index
−11.4
--
20
Z.ai (Zhipu AI) · 1,000,000 ctx · Open weights
28
−16 vs avg
28-28 index
−8.22
----
21
Xiaomi · 309B total, 15B active (sparse mixture of experts) params · 1,000,000 ctx · MIT — open weights (published as MiMo-V2.6-Flash-RL)
27
−17 vs avg
27-27 index
−9.22
----
22
Mistral AI · about 1T total (1.05T per Mistral docs), 52B active, plus 1.6B vision encoder params · 1,048,576 ctx · Mistral Ecosystem Open-Weight License (modified MIT; model-as-a-service providers need a commercial licence)
26
−18 vs avg
26-26 index
−10.22
----
23
Meta · 816B total parameters, 42B active per token (mixture of experts, 256 experts with 8 active per token) params · 1,000,000 ctx · Muse Model License
25
−19 vs avg
25-25 index
−11.22
----
24
DeepSeek · 1,000,000 ctx · Proprietary
23
−21 vs avg
23-23 index
−13.22
----
25
Alibaba · 27B params · 1,000,000 ctx · Qwen (open weights)
20
−24 vs avg
20-20 index
−16.22
----
26
NVIDIA · 120B total parameters, 12B active (hybrid Mamba-2, mixture of experts and attention layers, with a C-RADIO vision encoder) params · 1,000,000 ctx · OpenMDW-1.1
14
−30 vs avg
14-14 index
−22.22
----
27
IBM · 8B params · 512,000 ctx · Apache 2.0
5
−39 vs avg
5-5 index
−31.22
----
28100-------
2992
+48 vs avg
91----90.8 %
+0.9
-
30
OpenAI · 200,000 ctx · Proprietary
87-------
3185
+42 vs avg
90----90.2 %
+0.3
-
32
OpenAI · 128,000 ctx · Proprietary
84
+40 vs avg
89----88.7 %
−1.2
-
33
Google · 1,000,000 ctx · Proprietary
82-------
34
Anthropic · 1,000,000 ctx · Proprietary
78-------
3577
+33 vs avg
81-----80.5 %
36
xAI · 500,000 ctx · Proprietary
53
+9 vs avg
53--61 index44 index
−4.4
--
37
OpenAI · 1,050,000 ctx · Proprietary
48
+4 vs avg
48---48 index
−0.4
--
3842-------
3939-------
4036-------
4132-------
4231-------
4329-------
4428-------
4527-------
4625-------
4722-------
4821-------
4918-------
5017-------
5112-------
5211-------
5310-------
549-------
559-------
567-------
577-------
587-------
596-------
605-------
610-------
620-------
63
Agnes AI · 33B (open-weights Preview checkpoint; API model size not published) params · Apache 2.0 (Preview checkpoint weights)
0-------
64
Aikido Security · 504B total, ~40B active params · GLM-5.3 License — open weights
0-------
65
Cantina Security (with Yeta) · 321B total, 18B active (mixture of experts) params · 1,048,576 ctx · MIT
0-------
66
Ai2 · 8B params · Apache 2.0
0-------
67
Shanghai Artificial Intelligence Laboratory · 744B total, mixture of experts, built on GLM-5.2 (active parameters not published) params · 256,000 ctx · MIT
0-------
68
PrismML · 27B, compressed to ternary weights: 1.76 effective bits per weight and a 5.9 GB footprint params · 262,144 ctx · Apache 2.0
0-------
69
Anthropic · 1,000,000 ctx · Proprietary, API only
0-------
70
Anthropic · Proprietary
0-------
71
Anthropic · 1,000,000 ctx · Proprietary, access by application
0-------
72
Anthropic · 1,000,000 ctx · Proprietary
0-------
73
Cloudflare · 27B params · 64,000 ctx · Apache 2.0
0-------
74
Cloudflare · 9B params · 24,000 ctx · Apache 2.0
0-------
75
Cloudflare · 30B total, 3B active (mixture of experts) params · Apache 2.0
0-------
76
Contrastive-LM · 8B (frozen Qwen3-8B encoder with two small trained heads) params · Apache-2.0
0-------
770-------
780-------
79
Cua · 706,048 trainable parameters — a 2.8 MB checkpoint params · MIT — weights, training code and dataset published
0-------
80
Liquid AI · 3.12B params · 32,768 ctx · LFM Open License v1.0
0-------
81
Liquid AI · 587M params · 16,384 ctx · LFM Open License v1.0
0-------
820-------
830-------
84
VIDRAFT · 180B mixture of experts (10 of 512 routed experts active per token, plus a shared expert); a fine-tune of Qwen3.8-Flash-Next params · 262,144 ctx · Qwen Community License 1.0
0-------
85
CloudRaker · Proprietary
0-------
86
DeepSeek · 1,000,000 ctx
0-------
87
Nace AI · about 9B (8,953,803,264, BF16) params · 16,384 ctx · Nace.AI Open RAIL-M (modified Open RAIL-M; commercial use above set thresholds needs a separate licence)
0-------
88
ElevenLabs · Proprietary
0-------
89
ElevenLabs · Proprietary
0-------
90
Cohere · 128,000 ctx · Proprietary
0-------
91
Cohere · 128,000 ctx · Proprietary
0-------
92
Google · 740M (270M text-only core) params · 8,000 ctx · Apache 2.0
0-------
93
Fireworks AI · 2.78T (mixture of experts; the Kimi K3 base) params · 1,048,576 ctx · Proprietary
0-------
94
Baidu · 280B total, 14B active (sparse mixture of experts) params · 1,000,000 ctx · ERNIE 5.5 Flash Base Model License Agreement v1.0 (Baidu's own licence, open weights)
0-------
95
Technology Innovation Institute · 1.6B params
0-------
96
Black Forest Labs · 7B params · FLUX Kommunity License v1.0
0-------
97
Black Forest Labs · Commercial weights licence
0-------
98
Black Forest Labs · 5.6B parameters (image generator; text encoder not counted) params · FLUX Kommunity License (open weights)
0-------
990-------
100
Google · 1,000,000 ctx · Proprietary
0-------
101
Google · Restricted — Fairwind Program
0-------
102
Google · 8,192 ctx · Proprietary
0-------
103
Google · 8,192 ctx · Proprietary
0-------
104
Google · 131,072 ctx · Proprietary
0-------
105
Google · 131,072 ctx · Proprietary
0-------
106
Google · 1,048,576 ctx · Proprietary, API only
0-------
107
Google · 1,000,000 ctx
0-------
108
Google · 256,000 ctx · Proprietary, API only
0-------
109
Google · Proprietary, API only
0-------
110
Google · 131,072 ctx · Proprietary, API only
0-------
111
Elorian · Proprietary (API and chat UI); post-trained on an open-weights base model
0-------
112
Fastino · 340M (developer’s model card; the models page says 355M) params · Apache-2.0
0-------
113
Z.ai · 1,000,000 ctx · Proprietary — hosted tier, no weights of its own published
0-------
114
0-------
1150-------
1160-------
1170-------
118
OpenAI · 1,050,000 ctx · Proprietary, API only
0-------
119
OpenAI · 1,050,000 ctx
0-------
120
OpenAI · 1,050,000 ctx
0-------
121
IBM · 30B params · 512,000 ctx · Apache 2.0
0-------
122
IBM · Two sizes, built on the 8B and 30B Granite 4.1 base models, each with two activated-LoRA adapters and a 470M speech encoder params · 128,000 ctx · Apache 2.0
0-------
1230-------
124
Alibaba · Proprietary
0-------
125
Commons Lab (Hemmingway) · 27B params · 262,144 ctx · CC BY-NC 4.0
0-------
126
Tencent · about 30B total, about 3B active (mixture of experts, per the model name) params · Apache 2.0 (per the model card metadata)
0-------
127
Tencent · 1,048,576 ctx
0-------
128
Tencent · 220B total (155.5B plus 63.5B n-gram embeddings), 12B active per token; mixture of experts params · 1,048,576 ctx · Tencent Hy License 1.0 (custom, derived from Apache 2.0; separate licence needed for large hosted-API businesses)
0-------
129
Tencent · 770B total, 49B active (mixture of experts) params · 1,000,000 ctx
0-------
130
Bilibili (Index Team) · 35B total, 3B active (mixture of experts) params · Apache 2.0
0-------
131
Thinking Machines Lab · 26.4B total, 3.4B active (mixture of experts) params · 1,000,000 ctx · Apache 2.0
0-------
132
Thinking Machines Lab · 594B total, 17B active (mixture of experts) params · 256,000 ctx · Closed weights at release; Apache 2.0 weights promised by the vendor
0-------
133
InternLM · 0.8B, 2B and 4B (fine-tunes of Qwen3.5-0.8B, -2B and -4B) params · Apache-2.0
0-------
134
IQuestLab · 320B total, 15B active (mixture of experts, 8 of 256 experts per token) params · 524,288 ctx · Modified MIT (commercial products must display “IQuest-Q1”)
0-------
135
TypeSafe AI
0-------
136
Jared Palmer (individual) · 0.8B, 4B and 9B variants params · 8,192 ctx · Apache 2.0 — open weights
0-------
137
Moonshot AI · 1,048,576 ctx
0-------
138
Moonshot AI · 2.8T (104B active) params · 1,048,576 ctx · Kimi K3 License (open weights, not OSI)
0-------
139
Salesforce · Post-trained from NVIDIA Nemotron 3 Super, a 120-billion-parameter open model; Koa's own parameter count is not published params · Proprietary — Salesforce holds the weights and does not release them
0-------
140
Aleph Alpha · 78B total, 3B active (mixture of experts) params · 1,048,576 ctx · Apache 2.0
0-------
141
Convai Innovations · 421M (English checkpoint, ModernBERT-large encoder); 322M multilingual checkpoint (mmBERT-base) params · 512 ctx · Apache 2.0 — weights and the Python package
0-------
142
Interfaze · 4B (a LoRA adapter on Qwen3.5-4B) params · Apache-2.0
0-------
143
Liquid AI · 24B total parameters, about 2.45B active per token (mixture of experts, 64 experts per block, top-4 routing) params · 131,072 ctx · LFM 1.0
0-------
144
Liquid AI · 1.7B params · 256,000 ctx · LFM Open License v1.0
0-------
145
Light Origins · 5.5B (Hugging Face weight count; not stated by the developer) params · Apache 2.0 — open weights
0-------
146
Paradigma · 1B (dense) params · 131,072 ctx · Apache 2.0 — open weights
0-------
147
Stable AI · 400M params · stableai-limix-non-commercial-license-v1.0 — weights published, non-commercial use only
0-------
1480-------
1490-------
150
Microsoft · 1,000,000 ctx
0-------
151
Microsoft AI · Proprietary
0-------
152
Microsoft AI · Proprietary
0-------
153
Microsoft AI · Proprietary
0-------
154
JetBrains · 12B total, 2.5B active (mixture of experts) params · 131,072 ctx · Apache 2.0
0-------
155
Inception · 260,000 ctx
0-------
156
Inception · 1,000,000 ctx · Proprietary (API only)
0-------
157
Inception · 128,000 ctx · Proprietary
0-------
1580-------
159
inclusionAI · 6B params · MIT
0-------
160
inclusionAI · 6B params · MIT
0-------
161
Meta · 1,000,000 ctx · Proprietary, API only
0-------
162
Meta · 1,000,000 ctx · Proprietary
0-------
163
NaiveAI · 309B total, 15.5B active (mixture of experts) params · 1,000,000 ctx · MIT
0-------
164
NASA and IBM Research · Apache 2.0 — open weights
0-------
165
Cactus Compute · 121M (full network); deployable subnetworks from 2 to 20 layers params · Apache-2.0 — open weights
0-------
166
NVIDIA · 100M params · OpenMDW License Agreement v1.1
0-------
167
NVIDIA · 8.38B parameters params · 32,768 ctx · OpenMDW-1.1 (open weights)
0-------
168
NVIDIA · 8.38B parameters params · 32,768 ctx · OpenMDW-1.1 (open weights)
0-------
169
NVIDIA · about 30B total, about 4.3B active (mixture of experts, including the audio encoder) params · 65,536 ctx · OpenMDW-1.1 (open weights, commercial use allowed)
0-------
170
NVIDIA · 4B parameters; looped design with 8 input, 20 shared recurrent and 8 output layers params · 256,000 ctx · OpenMDW License Agreement 1.1
0-------
171
Unbiased AI · 262,144 ctx · Proprietary
0-------
172
Perceptron · 36,864 ctx · Proprietary
0-------
173
Klang AI · 0.6B params · CC BY 4.0
0-------
174
Perplexity · 27B params · 262,144 ctx · Apache 2.0
0-------
175
Alibaba Cloud · 262,144 ctx · Proprietary
0-------
176
Alibaba · 7B in the visual generation component (32 single-stream DiT layers) params · Qwen Research Licence — non-commercial only; commercial use needs a separate licence
0-------
177
Alibaba · 1,000,000 ctx · Proprietary
0-------
178
Alibaba Cloud (Qwen) · 1,000,000 ctx
0-------
179
Alibaba · 1,000,000 ctx · Proprietary — weights not released
0-------
180
Alibaba Cloud · 196,608 ctx · Proprietary
0-------
181
Alibaba Cloud · 1,000,000 ctx · Proprietary, Token Plan only, preview
0-------
182
Alibaba Cloud · 1,000,000 ctx · Proprietary, API only
0-------
183
Recraft · Proprietary
0-------
184
Ricursive Intelligence · 65B (dense) params · 1,048,576 ctx · Apache 2.0 (as tagged on Hugging Face)
0-------
185
ElevenLabs · Proprietary, API only
0-------
186
Upstage · 35B total, 3B active params · 524,288 ctx · Proprietary
0-------
187
AWS (Strands Agents) · 2B params · Apache 2.0
0-------
1880-------
189
Together AI · 4B params
0-------
190
BottleCap AI · 27.8B params · 262,144 ctx · PolyForm Small Business 1.0.0
0-------
191
Mistral AI · Four sizes: 5M, 28M, 123M and 209M parameters (patch-based transformer; the 209M model has 24 layers) params · 32,768 ctx · Modified MIT
0-------
192
Bad Theory Labs · 177B total, 6.6B active params · 262,144 ctx · Qwen Community License 1.0 — open weights
0-------
193
Baidu · 3.3B params · MIT
0-------
194
Mistral AI · Not stated (API, or self-deployment by arrangement)
0-------
195
Mistral AI · 4.4B params · Apache 2.0
0-------
196
Google DeepMind · Proprietary (Google Cloud access)
0-------
197
Tencent Youtu Lab · 5B params · Youtu-Parsing licence (custom; not intended for use within the European Union)
0-------

Score = hybrid of benchmark capability (60%), review rating (25%) and community votes (15%), renormalized by available signals. Capability is the mean of normalized benchmark results; green/red deltas compare each value to the average across benchmarked models. Official (editor-verified) and community-submitted values are kept separate - community submissions only affect rankings after editor approval. Your vote, rating and submitted stats all feed this score - sign-in required, so rankings stay hard to game.

Missing a model?

Suggest one and our editors will review and add it to the board.

Sign in to suggest a model
Launches

New AI model launches

The models that launched on TrustList this month, voted up by the community.

All AI launches
  • 1

    OpenAI's fast GPT-6.1 model for visual reasoning, computer use and writing, released 26 October 2026 at $1 input and $5 output per million tokens, with a 1.05M-token context and 128K output.

    TL score
  • 2

    Tencent Hunyuan's open-weight model for live Chinese and English interpreting, released 26 October 2026: it translates while the speaker talks and, with a separate TTS service, speaks in a clone of their voice.

    TL score
  • 3
    LFM3-1.7BAI model

    Liquid AI's open-weight 1.7-billion-parameter text model, released 27 October 2026 as the base of the LFM3 family, with a 256K context, about 1 GB at 4-bit, and fine-tuning on a single GPU.

    TL score
  • 4

    Baidu's open-weight document parsing model, released 27 October 2026 under the MIT licence, which reads every page of a long document in one request with near-constant memory per step.

    TL score
  • 5

    Google’s second Gemini 4 frontier model, announced 28 October 2026 and released first to cyber defenders through its Fairwind Program; $2 in and $10 out per million tokens at launch, then $4 and $20.

    TL score
  • 6

    NVIDIA's open-weight speech model, released 28 October 2026, transcribes and translates recordings of up to an hour in 40 languages, with speaker labels and word timestamps, on one H100 GPU.

    TL score
  • 7

    OpenAI's image generation and editing model for detailed visual work, released on 4 November 2026 with an adjustable complexity setting, markup-guided edits, SVG output and animated GIF output.

    TL score
  • 8

    OpenAI's image generation and editing model for fast, interactive iteration, released on 4 November 2026 beside Sunburst at the same token prices, with SVG and animated GIF output.

    TL score