Skip to content
IFAI

Model rankings

1539 models · 5 boards · 2 sources

‹
Week of September 28, 2026
November 9, 202636 changesNovember 2, 202641 changesOctober 26, 20269 changesOctober 19, 2026247 changesOctober 12, 2026127 changesOctober 5, 202634 changesSeptember 28, 202617 changesSeptember 21, 2026115 changesSeptember 14, 2026174 changesSeptember 7, 2026144 changesAugust 31, 202620 changesAugust 24, 202615 changes
›
Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated September 28, 2026

Smartest
Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)Anthropic57.6Intelligence
Best open model
MiMo-V2.6-ProXiaomi46.3Intelligence
Best value
Llama 3.1 Instruct 8BMeta252 pts/$Value
Best from China
MiMo-V2.6-ProXiaomi46.3Intelligence
Top three by Intelligence
1Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)Anthropic57.6
2Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)Anthropic53.4
3GPT-6 Astra (max)OpenAI52.7
Top three open models
1MiMo-V2.6-ProXiaomi · #10 overall46.3
2GLM-5.3 (max)Z AI · #12 overall44.8
3Kimi K3 (max)Kimi · #15 overall43.6
This week's changes
Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)Intelligence · #1New
Eleven v4Speech · #1New
Qwen-Audio-3.1-TTS-PlusSpeech · #2New
claude-sonnet-5.5-xhighCoding · #3New
gpt-6.1-sol-maxCoding · #4New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortIntelligenceValueSpeedLowest price
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1NewClaude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)ClosedAnthropic57.6$8.095683 s
2NewClaude Opus 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback)ClosedAnthropic56.0$8.088144 s
3NewClaude Opus 5.5 (Adaptive Reasoning, High Effort, Default Fallback)ClosedAnthropic53.6$8.08230 s
4▼ 3Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)ClosedAnthropic53.4$2069227 s
5▼ 3Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)ClosedAnthropic53.2$2066132 s
6▼ 3GPT-6 Astra (max)ClosedOpenAI52.7$2064268 s
7▼ 3GPT-6 Astra (xhigh)ClosedOpenAI52.4$205898 s
8NewClaude Opus 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback)ClosedAnthropic51.2$8.08213 s
9▼ 4Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)ClosedAnthropic51.2$205612 s
10▼ 4GPT-6 Astra (high)ClosedOpenAI50.9$206033 s
11▼ 4Claude Opus 5 (Adaptive Reasoning, Max Effort)ClosedAnthropic50.8$106135 s
12▼ 4Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)ClosedAnthropic49.7$105819 s
13▼ 4Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)ClosedAnthropic49.6$206399 s
14▼ 4GPT-6 Astra (medium)ClosedOpenAI49.6$20604.7 s
15▼ 4Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)ClosedAnthropic48.9$20567.6 s
16▼ 4Claude Opus 5 (Adaptive Reasoning, High Effort)ClosedAnthropic48.1$106110.0 s
17▼ 4Muse Spark 1.3 (max)ClosedMeta48.1$2.021026 s
18NewGPT-6 Sol (max)ClosedOpenAI47.5$4.089138 s
19▼ 5GPT-5.6 Sol (max)ClosedOpenAI47.0$8.09687 s
20▼ 5Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)ClosedAnthropic46.8$20565.5 s
21NewGrok 4.7 (xhigh)ClosedSpaceXAI46.4$3.08361 s
22NewGrok 4.7 (high)ClosedSpaceXAI46.3$3.08344 s
23▼ 7GPT-6 Astra (low)ClosedOpenAI45.8$20562.5 s
24▼ 7Qwen3.8 Max (0902)ClosedAlibaba45.4$3.0393.0 s
25▼ 7Muse Spark 1.3 (xhigh)ClosedMeta45.1$2.019629 s
26▼ 7Claude Opus 5 (Adaptive Reasoning, Medium Effort)ClosedAnthropic44.8$10615.3 s
27▼ 7Grok 4.6 (high)ClosedSpaceXAI44.3$3.06828 s
28▼ 7Grok 4.6 (xhigh)ClosedSpaceXAI44.2$3.07536 s
29NewGPT-6 Sol (xhigh)ClosedOpenAI44.1$4.08034 s
30▼ 8GPT-5.6 Sol (xhigh)ClosedOpenAI44.0$8.09222 s
31▼ 8Step 5 PreviewClosedStepFun43.7$1.4793.0 s
32▼ 8Grok 4.6 (medium)ClosedSpaceXAI42.8$3.06721 s
33NewGPT-6 Sol (high)ClosedOpenAI42.8$4.0838.5 s
34▼ 9GPT-5.6 Sol (high)ClosedOpenAI42.3$8.0846.0 s
35NewClaude Opus 5.5 (Adaptive Reasoning, Low Effort, Default Fallback)ClosedAnthropic42.3$8.0785.8 s
36▼ 10GPT-5.6 Terra (max)ClosedOpenAI42.1$4.5104139 s
37▼ 10Claude Opus 4.8 (Adaptive Reasoning, Max Effort)ClosedAnthropic41.8$10519.4 s
38▼ 10Gemini 3.8 Flash (high)ClosedGoogle40.9$1.531138 s
39▼ 10Claude Opus 4.7 (Adaptive Reasoning, Max Effort)ClosedAnthropic40.7$105014 s
40▼ 10Qwen3.8 MaxClosedAlibaba40.2$3.0373.0 s
41NewGPT-6 Sol (medium)ClosedOpenAI39.8$4.0——
42▼ 11Gemini 3.8 Flash (medium)ClosedGoogle39.8$1.5——
43▼ 11Gemini 3.7 Flash (medium)ClosedGoogle39.6$1.53076.1 s
44▼ 11Muse Spark 1.2 (xhigh)ClosedMeta39.6$2.023413 s
45▼ 11Claude Opus 5 (Adaptive Reasoning, Low Effort)ClosedAnthropic39.4$10632.9 s
46▼ 11GPT-5.6 Sol (medium)ClosedOpenAI39.2$8.0883.1 s
47▼ 11Gemini 3.7 Flash (high)ClosedGoogle39.1$1.532016 s
48▼ 11GPT-5.4 (xhigh)ClosedOpenAI39.0$5.6115133 s
49▼ 11Grok 4.5 (high)ClosedSpaceXAI38.8$3.0665.4 s
50▼ 11GPT-5.5 (xhigh)ClosedOpenAI38.4$1111039 s

Intelligence over time

Each maker's best model at the time on the Artificial Analysis Intelligence Index, by the month it was released.

Gained most · Anthropic +57.2Highest now · Anthropic 64.6Gap between highest and lowest 18.1 ptsTime range Nov 2025 – Nov 2026
64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi

Arena data comes from the leaderboard dataset it publishes on Hugging Face (CC BY 4.0). Only each board's overall leaderboard is used; scores and ranks are unchanged. dataset · CC BY 4.0

Artificial Analysis data comes from its API (artificialanalysis.ai). Scores are unchanged; ranks follow the scores. artificialanalysis.ai

Open or closed follows the license Arena gives; prices and Artificial Analysis intelligence show only where model names match, otherwise “—”.