Skip to content
TheBestSuperintelligence

Independent analysis · Artificial Analysis Intelligence Index v5.0

The frontier is a photo finish. Everyone else is racing for fourth.

Gemini 4 Carbon (high) leads with a 1-point margin, but it has no public API. The best model you can actually call is Claude Opus 5.5 (max w/ fallback) at 58. US labs hold 9 of the top 10 slots, and China's best trails the leader by 13 points.

By TheBestSuperintelligence Editorial Team · Data as of 2026-10-29

Top score59Gemini 4 Carbon (high)
Lead over #21Claude Opus 5.5 (max w/ fallback)
Best with public API58Claude Opus 5.5 (max w/ fallback)
Frontier-tier models7Score 50+
US-held top-10 slots9Out of the top 10 ranks
Field median32Across 28 ranked models
Market trends

Three models within a whisker, then a long slide

Every model in the snapshot, ranked by index score. Change the colour key to see who owns the ranking and which models you can't buy.

United StatesChinaRest of world
  1. 1Gemini 4 Carbon (high)no API59
  2. 2Claude Opus 5.5 (max w/ fallback)58
  3. 3GPT-6 Astra (max)57
  4. 4GPT-6.1 Sol (max)55
  5. 5Claude Sonnet 5.5 (max w/ fallback)54
  6. 6GPT-6.1 Terra (max)51
  7. 7Muse Wonder Full (max)no API50
  8. 8Claude Fable 5.1 (max w/ fallback)49
  9. 9Kimi K3.1 Pro46
  10. 10Muse Wonder (max)43
  11. 11Claude Haiku 5.5 (max)36
  12. 12Grok 4.7 (xhigh)34
  13. 13Qwen3.8 Max (0902)34
  14. 14DeepSeek V4.1 Flash 1017 (max)32
  15. 15GLM-5.3 (max)32
  16. 16Gemini 3.8 Flash (high)31
  17. 17MiMo-V2.6-Pro30
  18. 18Ling 3.1 Flash 101929
  19. 19MiniMax-M3.1-Flash29
  20. 20Step 5 Preview29
  21. 21GPT-6 Luna (max)28
  22. 22Mistral Large 4 (high)26
  23. 23Muse Spark Open (xhigh)25
  24. 24Qwen3.8 27B (xhigh)20
  25. 25K2 Horizon 375B A23B18
  26. 26Beam 1.018
  27. 27Nemotron 3.5 Super VL14
  28. 28Inkling (xhigh)12
Market structure

Four US labs own the frontier tier

Ranks only tell you who won. Depth tells you who can keep winning: how many strong models a lab ships and how many top-10 slots it holds.

Lab scorecard

One row per lab, sorted by its best model. Bar shows the best score.

LabBestAverageModelsTop 10
Google594521
Anthropic5849.343
OpenAI5747.843
Meta5039.332
Moonshot AI464611
xAI343410
Alibaba342720
DeepSeek323210
Z.ai323210
Xiaomi303010
Ant Group292910
MiniMax292910
StepFun292910
Mistral262610
MBZUAI181810
Beam181810
NVIDIA141410
Thinking Machines121210

Where the field sits

Models per score band. The frontier band is thin; the crowd lives in the middle.

  • Frontier50+7
  • Contender40–493
  • Mid-tier25–3913
  • Lightweightunder 255
  • The three busiest labs hold 8 of the top 10 slots.
  • Only 7 models clear the frontier band; all of them are American.
Geopolitics

China's labs cluster a full tier below the US frontier

US models spread from the very top to the very bottom. Chinese models bunch tightly in the low thirties, with one breakout.

Every model, by country

Each dot is a model. The tick marks each group's median; the dashed line marks the leader.

0102030405060Leader 59United Statesmedian 46Chinamedian 30Rest of worldmedian 18Gemini 4 Carbon (high): 59 (rank 1)Claude Opus 5.5 (max w/ fallback): 58 (rank 2)GPT-6 Astra (max): 57 (rank 3)GPT-6.1 Sol (max): 55 (rank 4)Claude Sonnet 5.5 (max w/ fallback): 54 (rank 5)GPT-6.1 Terra (max): 51 (rank 6)Muse Wonder Full (max): 50 (rank 7)Claude Fable 5.1 (max w/ fallback): 49 (rank 8)Kimi K3.1 Pro: 46 (rank 9)Muse Wonder (max): 43 (rank 10)Claude Haiku 5.5 (max): 36 (rank 11)Grok 4.7 (xhigh): 34 (rank 12)Qwen3.8 Max (0902): 34 (rank 13)DeepSeek V4.1 Flash 1017 (max): 32 (rank 14)GLM-5.3 (max): 32 (rank 15)Gemini 3.8 Flash (high): 31 (rank 16)MiMo-V2.6-Pro: 30 (rank 17)Ling 3.1 Flash 1019: 29 (rank 18)MiniMax-M3.1-Flash: 29 (rank 19)Step 5 Preview: 29 (rank 20)GPT-6 Luna (max): 28 (rank 21)Mistral Large 4 (high): 26 (rank 22)Muse Spark Open (xhigh): 25 (rank 23)Qwen3.8 27B (xhigh): 20 (rank 24)K2 Horizon 375B A23B: 18 (rank 25)Beam 1.0: 18 (rank 26)Nemotron 3.5 Super VL: 14 (rank 27)Inkling (xhigh): 12 (rank 28)

US vs China, head to head

Best against best, then the typical model against the typical model.

Best US model59
Best Chinese model46
Median US model46
Median Chinese model30
China's top-10 slots1

Kimi K3.1 Pro is the only non-US model in the top 10, at rank 9.

Financial impact

The price of going small is steep

Every lab sells a cheaper tier. This shows how much capability you give up to get it: each line runs from a lab's weakest model in the snapshot to its strongest.

Flagship vs lightest model, per lab

Labs with two or more models in the snapshot, longest drop first.

0102030405060OpenAIGPT-6 Luna (max): 28GPT-6 Astra (max): 57−29GoogleGemini 3.8 Flash (high): 31Gemini 4 Carbon (high): 59−28MetaMuse Spark Open (xhigh): 25Muse Wonder Full (max): 50−25AnthropicClaude Haiku 5.5 (max): 36Claude Opus 5.5 (max w/ fallback): 58−22AlibabaQwen3.8 27B (xhigh): 20Qwen3.8 Max (0902): 34−14

What this means for spend Our analysis

  • Steepest drop: OpenAI, 29 points from flagship to lightest model. Budget tiers are a different product, not a discount.
  • Paying for the best callable model costs you 1 point against the unreleased leader. The premium for the gated model buys almost nothing.
  • The top three sit within 2 points. At the frontier, negotiate on price and latency, not capability.
  • China's best scores 46, beating Claude Haiku, Gemini Flash and GPT-6 Luna outright. That is the cost-arbitrage zone.

The index has no price data. Pair these gaps with per-token pricing before committing spend.

Technological risks and opportunities

What to act on

Opportunities Our analysis

  • The frontier is buyable: 5 of 7 frontier-tier models have a public API.
  • Low lock-in at the top. Three vendors within 2 points makes multi-model routing cheap to adopt.
  • A non-US option exists near the top: Kimi K3.1 Pro at rank 9.
  • The mid-tier is crowded, so prices there should fall fastest. Half the field scores 32 or less.

Risks Our analysis

  • The #1 model is gated. 2 models in the snapshot have no public API, and both sit in the frontier tier.
  • Concentration: three labs hold 8 of the top 10 slots. Supplier risk sits with very few companies.
  • Small-model cliff: going light costs up to 29 points. Agentic and coding work will feel it first.
  • Geopolitical exposure: the US–China gap at the top is 13 points, and export rules can widen or close it overnight.

Sources and limits

Scores are transcribed from the Artificial Analysis Intelligence Index v5.0 chart shared on 2026-10-29 (nine evaluations including Terminal-Bench 4.0, FrontierCode 2.0, HLE-Diamond and GDP.pdf). We re-checked all 28 scores, the index version and the #1 position against Artificial Analysis's published leaderboard on 2026-10-30, and they match. We did not re-check the API-access flags. "No public API" follows the chart's checkered marking. Lab and country tags, score bands and all commentary are this report's own analysis, not Artificial Analysis's. Related reading: how to compare frontier AI models without a leaderboard and the companies building frontier AI.