RANK

Which model should you choose, and why?

Rank is the decision surface of SUPERCRZY. It separates intelligence, usage heat, and coding strength so one recommendation does not flatten three different kinds of judgment.

Updated Oct 4, 2026 7 live ranking views Global board in progress

LIVE BOARD

Switch the lens, then read the board

Each board is refreshed from its source as new snapshots land — check the snapshot date shown on the board you are reading. Source data is published by third parties and is shown here for reference.

Primary source: Artificial Analysis — 2026-10-04Snapshot: AA Intelligence Index — 2026-10-04Use case: general intelligence
#ModelVendorCountryScore0%30%60%PriceSpeed
🥇Claude Opus 5.5 (Max, Default Fallback)AnthropicUS
58
898
🥈Claude Sonnet 5.5 (Max, Default Fallback)AnthropicUS
56
4143
🥉Claude Opus 5.5 (Xhigh, Default Fallback)AnthropicUS
56
880
#4Claude Opus 5.5 (High, Default Fallback)AnthropicUS
54
878
#5Claude Fable 5.1 (Max, Default Fallback)AnthropicUS
53
2070
#6Claude Fable 5.1 (Xhigh, Default Fallback)AnthropicUS
53
2061
#7GPT-6 Astra (Max)OpenAIUS
53
2061
#8Gemini 4 Argon (High)GoogleUS
53
40
#9GPT-6 Astra (Xhigh)OpenAIUS
52
2060
#10Claude Sonnet 5.5 (Xhigh, Default Fallback)AnthropicUS
52
4110
#11GPT-6.1 Sol (Max)OpenAIUS
52
459
#12Claude Opus 5.5 (Medium, Default Fallback)AnthropicUS
51
878
#13Claude Fable 5.1 (High, Default Fallback)AnthropicUS
51
2058
#14GPT-6.1 Sol (Xhigh)OpenAIUS
51
454
#15GPT-6 Astra (High)OpenAIUS
51
2054
#16Claude Opus 5 (Max)AnthropicUS
51
100
#17GPT-6.1 Sol (High)OpenAIUS
50
452
#18Claude Opus 5 (Xhigh)AnthropicUS
50
100
#19Claude Fable 5 (Max, Opus 4.8 Fallback)AnthropicUS
50
200
#20GPT-6 Astra (Medium)OpenAIUS
50
2055
#21Claude Fable 5.1 (Medium, Default Fallback)AnthropicUS
49
2059
#22Claude Opus 5 (High)AnthropicUS
48
100
#23Muse Spark 1.3 (Max)MetaUS
48
2165
#24GPT-6.1 Sol (Medium)OpenAIUS
48
456
#25GPT-6 Sol (Max)OpenAIUS
48
4129
#26GPT-5.6 Sol (Max)OpenAIUS
47
80
#27Claude Fable 5.1 (Low, Default Fallback)AnthropicUS
47
2055
#28Claude Sonnet 5.5 (High, Default Fallback)AnthropicUS
47
4109
#29Grok 4.7 (Xhigh)SpaceXAIUS
46
382
#30Grok 4.7 (High)SpaceXAIUS
46
378
#31MiMo-V2.6-ProXiaomiCN
46
0.5446
#32GPT-6 Astra (Low)OpenAIUS
46
2054
#33Qwen3.8 Max (0902)AlibabaCN
45
337
#34Muse Spark 1.3 (Xhigh)MetaUS
45
2172
#35Claude Opus 5 (Medium)AnthropicUS
45
100
#36GLM-5.3 (Max)Z AICN
45
2.1576
#37Grok 4.6 (High)SpaceXAIUS
44
30
#38GPT-6 Sol (Xhigh)OpenAIUS
44
4128
#39Grok 4.6 (Xhigh)SpaceXAIUS
44
30
#40GPT-5.6 Sol (Xhigh)OpenAIUS
44
80
#41Step 5 PreviewStepFunCN
44
1.4384
#42Kimi K3 (Max)Kimi
44
635
#43Grok 4.6 (Medium)SpaceXAIUS
43
30
#44GPT-6 Sol (High)OpenAIUS
42
4119
#45GPT-5.6 Sol (High)OpenAIUS
42
80
#46Claude Opus 5.5 (Low, Default Fallback)AnthropicUS
42
878
#47Grok 4.7 (Low)SpaceXAIUS
42
368
#48GPT-6.1 Sol (Low)OpenAIUS
42
452
#49GPT-5.6 Terra (Max)OpenAIUS
42
4.5112
#50GLM 5.3 FlashZ AICN
42
0.2454
#51Claude Opus 4.8 (Max)AnthropicUS
42
100
#52Ling 3.1 FlashInclusionAICN
41
0.45218
#53Gemini 3.8 Flash (High)GoogleUS
41
1.5256
#54Claude Sonnet 5.5 (Medium, Default Fallback)AnthropicUS
41
4111
#55Claude Opus 4.7 (Max)AnthropicUS
41
100
#56Qwen3.8 MaxAlibabaCN
40
30
#57Qwen3.8 2.4T A95BAlibabaCN
40
339
#58Qwen3.8-Flash-NextAlibabaCN
40
0.2353
#59GPT-6 Sol (Medium)OpenAIUS
40
40
#60Gemini 3.8 Flash (Medium)GoogleUS
40
1.50
#61Gemini 3.7 Flash (Medium)GoogleUS
40
1.50
#62Muse Spark 1.2 (Xhigh)MetaUS
40
20
#63DeepSeek V4.1 Flash (Max)DeepSeekCN
40
0.53215
#64Claude Opus 5 (Low)AnthropicUS
39
100
#65GPT-5.6 Sol (Medium)OpenAIUS
39
80
#66Gemini 3.7 Flash (High)GoogleUS
39
1.50
#67GPT-5.4 (Xhigh)OpenAIUS
39
5.630
#68Grok 4.5 (High)SpaceXAIUS
39
30
#69GPT-5.5 (Xhigh)OpenAIUS
38
11.250
#70Claude Sonnet 5 (Max)AnthropicUS
38
40
#71GPT-6 Luna (Max)OpenAIUS
38
0.2136
#72GPT-5.6 Terra (Xhigh)OpenAIUS
38
4.5105
#73MiMo-V2.6-FlashXiaomiCN
38
0.1757
#74GPT-5.6 Luna (Max)OpenAIUS
37
0.450
#75GPT-5.5 (High)OpenAIUS
37
11.250
#76Gemini 3.7 Flash (Low)GoogleUS
37
1.50
#77DeepSeek V4 Pro 0813 (Max)DeepSeekCN
36
1.98116
#78Claude Sonnet 5.5 (Low, Default Fallback)AnthropicUS
36
4107
#79Grok 4.6 (Low)SpaceXAIUS
35
30
#80DeepSeek V4 Flash Vision (Max)DeepSeekCN
35
0.66220
#81GPT-6 Luna (Xhigh)OpenAIUS
35
0.2137
#82GPT-5.6 Luna (Xhigh)OpenAIUS
35
0.450
#83Claude Sonnet 5 (Xhigh)AnthropicUS
34
40
#84DeepSeek V4 Flash 0731 (Max)DeepSeekCN
34
0.660
#85GLM-5.3 (Low)Z AICN
34
2.1576
#86GPT-5.6 Terra (High)OpenAIUS
34
4.5105
#87GPT-6 Sol (Low)OpenAIUS
34
495
#88Gemini 3.6 Flash (High)GoogleUS
34
1.50
#89JT-4.1 Flash 236B A21B (Reasoning)China MobileCN
34
00
#90GPT-5.5 (Medium)OpenAIUS
34
11.250
#91Muse Spark 1.1 (Xhigh)MetaUS
34
20
#92GLM-5.2 (Max)Z AICN
34
2.150
#93Qwen3.8 27B (Xhigh)AlibabaCN
34
1.1347
#94Gemini 3.5 Flash (Medium)GoogleUS
34
3.380
#95Motif 3Motif Technologies
34
00
#96GPT-5.6 Sol (Low)OpenAIUS
34
80
#97Gemini 3.8 Flash (Low)GoogleUS
34
1.50
#98GPT-6 Luna (High)OpenAIUS
33
0.2132
#99Gemini 3.5 Flash (High)GoogleUS
33
3.380
#100GPT-5.3 Codex (Xhigh)OpenAIUS
33
4.81105
Advertisement

Source notes

Where these snapshots come from

Capability draws from Artificial Analysis, Usage Heat from OpenRouter routing, and Coding from SWE-bench-style score snapshots with explicit provenance.

Best quick take

Start with capability, then ask whether heat confirms it.

If a model is hot but weak on coding, do not over-recommend it for engineering workflows.

What changes next

Watch Chinese labs, agent-ready releases, and coding-specific jumps.

The most meaningful movement usually shows up in heat and coding before it settles into broad capability rankings.

AGENT HANDOFF

Rank should end with a better decision, and sometimes that decision needs an agent.

Once a reader understands the model tradeoffs, the deeper step may be asking an agent to help compare workflows, narrow choices, or move into actual execution.

See Agent landscape Open SuperCrzy Agent

CRAZE

Don't let the board boss you around. CRAZE can turn raw scores into a clearer recommendation.

Explore CRAZE