Name: Claude Sonnet 5.5
Price: 2 USD
Author: Anthropic

Rank	Model	Overall score	Artificial Analysis	LiveBench	Epoch AI	ARC-AGI	Scale SEAL	Vals AI	Terminal-Bench	EQ-Bench	SimpleBench	BenchLM
1	Claude Opus 5.5 Anthropic	92.2	#1	#2	—	#2	—	#1	—	—	#1	—
2	GPT-6 Astra OpenAI	91.9	#4	#4	#1	#1	#1	#5	#1	—	#4	#1
3	Claude Fable 5.1 Anthropic	91.4	#3	#1	#2	#5	#2	#3	#2	—	#2	#2
4	Claude Fable 5 Anthropic	90.3	#6	#3	#3	#7	—	#6	#4	#2	—	#4
5	Claude Opus 5 Anthropic	89.9	#5	#9	#4	#4	—	#4	#3	#1	#8	#3
6	Muse Spark 1.3 Meta	88.6	#7	#5	#15	—	—	#7	—	—	#7	—
7	Claude Sonnet 5.5 Anthropic	88.1	#2	#19	—	—	—	#2	—	—	—	—
8	GPT-5.6 Sol OpenAI	87.6	#9	#6	#6	#3	—	#8	#7	#9	#23	#5
9	GPT-6 Sol OpenAI	86.6	#8	#11	—	#6	—	#9	—	—	#15	—
10	GPT-5.5 Pro OpenAI	86.4	—	—	#5	#10	—	—	—	—	#10	—
11	GPT-5.4 Pro OpenAI	84.7	—	—	#9	#14	—	—	—	—	—	—
12	MiMo V2.6 Pro Xiaomi	84.5	#11	—	—	—	—	#17	—	—	—	—
13	DeepSeek V4.1 Flash DeepSeek	84.2	#23	#6	#28	—	—	#21	—	—	#21	—
14	Grok 4.7 xAI	84.2	#10	#20	—	—	—	#12	#6	—	—	—
15	GPT-5.5 OpenAI	83.9	#26	#8	#8	#9	—	#23	—	#4	#19	#11
16	Gemini 3.8 Flash Google	82.9	#20	#31	#13	#7	#4	#10	#11	—	#5	#6
17	Kimi K3 Moonshot AI	82.8	#16	#11	#12	#25	—	#22	—	#3	#33	#8
18	Qwen 3.8 Max Alibaba (Qwen)	81.9	#12	#14	#26	—	—	#34	—	—	—	#9
19	Grok 4.6 xAI	81.9	#14	#15	#18	#21	—	#19	#10	—	#13	#11
20	GPT-5.4 OpenAI	81.7	—	#15	#14	#17	—	—	—	#7	—	#13
21	Gemini 3.7 Flash Google	81.6	#24	#13	#11	#10	—	#18	#15	—	—	#14
22	GPT-5.6 Terra OpenAI	81.6	#17	#18	#7	#13	—	#14	#9	#11	#53	#7
23	Muse Spark 1.2 Meta	81.5	#22	#15	#27	—	—	#24	—	—	#14	—
23	GLM-5.3 Z.ai (Zhipu)	81.5	#13	#29	#22	—	—	#25	#5	—	#22	—
25	Claude Opus 4.8 Anthropic	80.9	#18	#27	#10	#18	—	#11	#8	#6	#23	#10
26	MiMo V2.6 Flash Xiaomi	80.2	#28	—	—	—	—	#14	—	—	—	—
27	Claude Opus 4.7 Anthropic	79.6	—	#26	#19	#16	#9	#26	—	#5	#26	—
28	Qwen 3.8 Flash Next Alibaba (Qwen)	78.2	#21	#27	—	—	—	—	—	—	—	—
29	Claude Sonnet 5 Anthropic	77.3	#27	#30	#20	—	—	#14	#13	#10	#34	#15
30	Gemini 3.1 Pro Google	76.6	#41	#23	#29	#15	#3	#42	—	#21	#9	—
31	DeepSeek V4 Pro DeepSeek	75.5	#31	#20	#24	#24	—	#33	—	#18	#51	—
32	Muse Spark 1.1 Meta	75.5	#35	#33	#33	—	—	#29	—	#8	—	#16
33	Grok 4.5 xAI	74.9	#25	#31	#34	#33	—	#35	#13	—	#18	#18
34	Claude Opus 4.6 Anthropic	74.2	—	#37	#25	#20	#10	—	—	#13	#20	#20
35	Muse Spark Meta	73.6	—	—	#39	—	#6	—	—	—	—	#27
36	Gemini 3.5 Flash Google	73.4	#38	#35	#30	#18	—	#31	—	#24	#11	#21
36	DeepSeek V4 Flash DeepSeek	73.4	#33	#38	#31	#23	—	#30	—	—	#31	—
38	GPT-5.6 Luna OpenAI	73.2	#29	#40	#21	#29	—	#13	#12	#19	#55	#17
39	Gemini 3.6 Flash Google	73.1	#34	#40	#32	#25	—	#27	—	—	—	#19
40	GPT-6 Luna OpenAI	73.0	#29	#46	—	#30	—	#20	—	—	—	—
41	Qwen3.8 27B Alibaba (Qwen)	72.8	#35	#33	—	—	—	#37	—	—	—	—
42	Gemini 3 Pro Google	69.7	—	—	#37	#38	#7	—	—	—	#12	#26
43	GPT-5.2.11 OpenAI	69.3	—	#35	—	—	#12	—	—	—	—	—
44	GPT-5.3 Codex OpenAI	69.3	—	—	#16	—	—	—	—	—	—	#24
45	GLM-5.3 Flash Z.ai (Zhipu)	69.0	#18	#48	#41	—	—	#38	—	—	—	—
46	GPT-5.2 Pro OpenAI	68.8	—	—	#23	#31	—	—	—	—	#41	—
47	Claude Sonnet 4.6 Anthropic	68.1	#40	#44	#38	#25	—	#36	—	#16	—	#30
48	GLM-5.2 Z.ai (Zhipu)	67.9	#35	#42	#43	#39	—	#31	—	#14	#38	#23
49	Qwen 3.7 Max Alibaba (Qwen)	65.6	#42	#43	#35	—	—	#39	—	#23	—	#22
50	Qwen 3.6 Max Alibaba (Qwen)	65.2	—	—	#53	—	—	—	—	—	#25	—

Rank	Provider	Overall score	Top model	Models
1	Anthropic	86.7	Claude Opus 5.5	28
2	OpenAI	85.2	GPT-6 Astra	54
3	Meta	77.7	Muse Spark 1.3	23
4	Google	74.4	Gemini 3.8 Flash	33
5	xAI	72.6	Grok 4.7	13
6	Xiaomi	70.0	MiMo V2.6 Pro	4
7	Moonshot AI	69.8	Kimi K3	5
8	Alibaba (Qwen)	68.1	Qwen 3.8 Max	46
9	DeepSeek	67.8	DeepSeek V4.1 Flash	22
10	Z.ai (Zhipu)	66.0	GLM-5.3	10
11	Tencent	53.3	—	2
12	Thinking Machines	42.1	Inkling	2
13	MiniMax	40.3	Minimax M3	5
14	Ant Group	32.7	—	5
15	NVIDIA	29.7	Nemotron 3 Ultra 550B A55B	10
16	Mistral AI	17.6	Mistral 3.5	26
17	Microsoft	16.7	Phi-4	6
18	Amazon	15.8	—	3
19	Inception	13.4	Mercury 2.5	1
20	Cohere	12.8	Command R	3

A provider’s result on each site is that of its best model there.

Performance vs price

Top left = cheap and strong. Click a point for details.

Best value

Overall score ÷ price

Top open-weight models

Models with public weights

Fastest models

Output tokens per second

By country

Top 50 models

Agreement between leaderboards

Rank correlation on shared models (1 = identical).

How the ranking works

Collect — Official data from the 11 leaderboards below is fetched every hour. Scores marked as estimates are not used.
Match — Different spellings of the same model are merged. For variants such as reasoning effort, each site’s best result is used.
Standardize — Each site’s main metric is standardized within that site, keeping score gaps rather than just ranks.
Equate — A factor model, bridged by models listed on several sites, corrects for each site’s difficulty and model mix. Noisier sites get less weight.
No penalty for missing data — Models are scored only from the sites that rated them. Uncertainty is shown as a 90% interval. Models rated on 2+ sites are ranked.
Arena — Arena (formerly LMArena) is used for domain rankings only, not for the overall score. New models are added automatically.

Leaderboard	Rank	Published value
Artificial Analysis	#2 / 110	56
LiveBench	#19 / 60	77.8
Epoch AI	Not rated	—
ARC Prize (ARC-AGI)	Not rated	—
Scale AI SEAL	Not rated	—
Vals AI	#2 / 64	69.2
Terminal-Bench	Not rated	—
EQ-Bench	Not rated	—
SimpleBench	Not rated	—
BenchLM.ai	Not rated	—

Claude Sonnet 5.5: benchmarks and ranking

Rank on each leaderboard

Domain scores