Text Rankings

This page shows Arena AI A daily snapshot of the top 30 on the leaderboard, making it easy to quickly understand recent model performance. For the full leaderboard, filters, and latest changes, please visit the Arena AI official website.

This leaderboard is Arena AI's core text battle leaderboard, which estimates models' relative strength based on human blind-vote battles.

Data updated at: 2026-09-01 13:25:31 UTC / 2026-09-01 21:25:31 CST (Beijing time)

The leaderboard reflects specific evaluations and user voting preferences, and does not necessarily mean a model will perform better on your task. When choosing a model, you should also consider price, speed, context length, tool calling, privacy, and regional availability.

Top 30

Rank	Rank range	Model	Score	Votes	Price $/million Token	Context
1	1-4	claude-fable-5 1	1507 (±5)	25,824	$10 / $50	1M
2	1-4	claude-opus-4-6-high 1	1505 (±4)	72,104	$5 / $25	1M
3	1-5	claude-opus-4-7-high 1	1502 (±4)	60,136	$5 / $25	1M
4	1-15	muse-spark-1.2 (xHigh) 1	1498 (±10)	3,247	$1.25 / $4.25	N/A
5	3-11	claude-opus-4-6 1	1497 (±3)	76,079	$5 / $25	1M
6	4-13	claude-opus-4-7 1	1494 (±4)	61,282	$5 / $25	1M
7	4-16	claude-opus-5-high 1	1492 (±5)	31,570	$5 / $25	1M
8	4-20	muse-spark-1.1 1	1490 (±5)	22,215	$1.25 / $4.25	N/A
9	4-22	gemini-3.7-flash-high 1	1490 (±8) Preliminary	5,720	$0.75 / $3.57	1M
10	4-22	kimi-k3-max 1	1489 (±6)	16,586	N/A	N/A
11	4-22	muse-spark 1	1488 (±6)	13,574	N/A	N/A
12	5-22	claude-opus-5-max 1	1488 (±6)	15,398	$5 / $25	1M
13	6-21	gemini-3.1-pro-preview 1	1487 (±3)	101,163	$1 / $6	1M
14	6-22	gemini-3-pro 1	1486 (±4)	40,674	$2 / $12	1M
15	5-34	glm-5.3-max 1	1484 (±8)	5,820	$1.40 / $4.40	1M
16	8-28	gpt-5.5-high 1	1482 (±4)	61,604	$5 / $30	1.1M
17	7-31	gpt-5.6-sol-xhigh 1	1482 (±5)	21,537	$4 / $20	N/A
18	8-31	claude-opus-4-8-high 1	1481 (±4)	46,773	$5 / $25	1M
19	8-35	gemini-3.6-flash-high 1	1481 (±5)	20,190	$0.75 / $3.75	1M
20	8-37	qwen3.8-max 1	1479 (±6)	11,780	$2 / $6	1M
21	10-36	gemini-3.5-flash-high 1	1479 (±4)	32,174	$0.75 / $4.50	1M
22	15-37	gpt-5.5 1	1477 (±4)	62,975	$5 / $30	1.1M
23	15-38	gpt-5.4-high 1	1477 (±4)	60,614	$2.50 / $15	1.1M
24	15-39	gpt-5.2-chat-latest-20260210 1	1476 (±4)	34,229	$1.75 / $14	128K
25	15-45	grok-4.20-beta1 1	1475 (±5)	26,645	N/A	N/A
26	16-46	gemini-3-flash 1	1474 (±4)	30,242	$0.50 / $3	1M
27	9-50	qwen3.7-max-preview 1	1474 (±10)	3,712	$1.48 / $4.42	1M
28	16-46	gemini-3.5-flash-medium 1	1473 (±5)	30,593	$0.75 / $4.50	1M
29	15-48	gpt-5.5-instant 1	1473 (±5)	25,857	$5 / $30	1.1M
30	18-46	claude-opus-4-5-20251101-high-32k 1	1473 (±4)	36,267	$5 / $25	200K

How to read this table

• Rank / Rank range: The relative ranking estimated by Arena AI based on battle votes; the rank range indicates rank fluctuations within the confidence interval.
• Score: Relative score, suitable for comparing models in the leaderboard at the same time.
• Votes / sessions: Sample size reference; with fewer samples, rankings tend to fluctuate more easily.
• Price $/million Token: Reference price per million input / output tokens.
• Context: Maximum context length supported by the model.

Three things to confirm when choosing a model

1. Whether the provider actually offers this model, and whether it is available in your region and account;
2. Whether the API price, rate limits, and context length fit your task;
3. Run a small-scale test with 3 to 5 real tasks; don't look only at the overall leaderboard rank.

Data source

Data from Arena AI official text leaderboard, updated daily by GitHub Actions. For model pricing, licenses, and capabilities, please refer to the model provider's official information.