Knowledge & language Text Model Leaderboard

Factual accuracy, long-context understanding, language, instruction following, and false-premise detection.


1	OPGPT-6 Astra	Sep 3, 2026	100%27 items	$1	$10	$50	73.8
2	OPGPT-6.1 Sol	Oct 8, 2026	100%27 items	$0.1	$2	$10	72.2
3	ANClaude Opus 5.5	Sep 22, 2026	100%27 items	$5	$4	$20	69.3
4	ANClaude Fable 5.1	Sep 1, 2026	100%26 items	$12.5	$10	$50	67.6
5	ANClaude Sonnet 5.5	Sep 28, 2026	100%27 items	$2.5	$2	$10	66.3
6	OPGPT-6.1 Terra	Oct 26, 2026	80%18 items	$0.05	$1	$5	65.9
7	OPGPT-5.6 Sol	Jul 9, 2026	80%25 items	$0.4	$4	$20	65.7
8	OPGPT-6 Sol	Sep 22, 2026	100%25 items	$0.2	$2	$10	65.3
9	GOGemini 4 Argon	Sep 30, 2026	100%27 items	$0.1	$2	$10	65.2
10	ALQwen3.8 Max	Aug 3, 2026	80%23 items	$0.25	$2	$6	65.0
11	ANClaude Opus 4.8	May 28, 2026	80%22 items	$6.25	$5	$25	64.0
12	OPGPT-5.5	Apr 23, 2026	80%20 items	$0.5	$5	$30	63.8
13	ANClaude Fable 5	Jun 9, 2026	80%22 items	$12.5	$10	$50	63.3
14	ANClaude Opus 5	Jul 24, 2026	100%26 items	$6.25	$5	$25	62.5
15	GOGemini 3.8 Flash	Sep 2, 2026	80%26 items	$0.075	$0.75	$3.75	62.2
16	XAGrok 4.7	Sep 21, 2026	80%26 items	$0.5	$2	$6	61.9
17	STStep 5 Preview	Sep 20, 2026	60%19 items	¥0.35	¥7	¥20	59.7
18	ALQwen3.7 Max	May 21, 2026	80%17 items	$0.5	$2.5	$7.5	59.6
19	XAGrok 4.6	Aug 12, 2026	100%26 items	$0.5	$2	$6	59.5
20	MAKimi K3	Jul 16, 2026	100%26 items	$3	$3	$15	59.4
21	DEDeepSeek V4.1 Flash	Sep 10, 2026	80%25 items	$0.003	$0.15	$0.6	58.9
22	MEMuse Spark 1.3	Sep 2, 2026	60%24 items	$0.15	$1.25	$4.25	58.7
23	ANClaude Haiku 5.5	Oct 7, 2026	100%27 items	$0.125	$0.1	$0.5	57.8
24	DEDeepSeek V4.1 Flash 1017	Oct 17, 2026	80%21 items	$0.003	$0.15	$0.6	57.0
25	XAGrok 4.5	Jul 8, 2026	80%20 items	$0.3	$2	$6	56.2
26	ZAGLM 5.3	Oct 5, 2026	100%27 items	$0.26	$1.4	$4.4	56.0
27	OPGPT-6 Luna	Sep 22, 2026	100%27 items	$0.01	$0.1	$0.5	55.9
28	OPGPT-5.6 Terra	Jul 9, 2026	100%24 items	$0.2	$2	$12	55.9
29	ANClaude Sonnet 4.6	Feb 17, 2026	80%19 items	$3.75	$3	$15	55.6
30	GOGemini 3.6 Flash	Jul 21, 2026	80%20 items	$0.075	$0.75	$3.75	55.6
31	MEMuse Spark 1.2	Aug 5, 2026	80%18 items	$0.15	$1.25	$4.25	54.7
32	GOGemini 3.5 Flash Lite	Jul 21, 2026	80%21 items	$0.03	$0.3	$2.5	54.4
33	MEMuse Spark 1.1	Apr 8, 2026	60%16 items	$0.15	$1.25	$4.25	53.8
34	ANClaude Sonnet 5	Jun 30, 2026	80%22 items	$2.5	$2	$10	53.3
35	XIMiMo-V2.5-Pro	Apr 22, 2026	60%15 items	$0.0036	$0.435	$0.87	53.2
36	MAKimi K2.6	Apr 21, 2026	80%18 items	$0.16	$0.95	$4	53.1
37	MIMiniMax M3.1 Flash	Oct 19, 2026	60%15 items	$0.015	$0.15	$0.6	52.5
38	XIMiMo V2.6 Pro	Sep 21, 2026	60%21 items	$0.0036	$0.435	$0.87	52.2
39	DEDeepSeek V4 Pro 0813	Aug 13, 2026	80%23 items	$0.022	$0.66	$1.98	51.8
40	ZAGLM-5.3 Flash	Aug 26, 2026	60%24 items	$0.03	$0.15	$0.5	51.5
41	XIMiMo-V2.5	Apr 22, 2026	40%12 items	$0.0028	$0.14	$0.28	51.4
42	XAGrok 4.3	Apr 17, 2026	60%15 items	$0.2	$1.25	$2.5	51.3
43	MIMiniMax-M3	Jun 1, 2026	80%21 items	$0.06	$0.3	$1.2	51.0
44	OPGPT-5.6 Luna	Jul 9, 2026	100%25 items	$0.02	$0.2	$1.2	50.9
45	MAKimi K2.7 Code	Jun 12, 2026	60%15 items	$0.19	$0.95	$4	50.5
46	DEDeepSeek V4 Flash 0731	Jul 31, 2026	60%18 items	Unverified	$0.016	$0.64	50.0
47	OPGPT-5.4 mini	Mar 17, 2026	80%20 items	$0.075	$0.75	$4.5	49.9
48	ALQwen3.7 Plus	Jun 2, 2026	40%14 items	$0.05	$0.4	$1.6	49.7
49	ZAGLM-5.2	Jun 13, 2026	80%19 items	$0.26	$1.4	$4.4	48.3
50	TMInkling	Jul 15, 2026	80%23 items	$0.374	$1.87	$4.68	47.4
51	INLing-3.0-flash (free)	Jul 23, 2026	40%11 items	Unverified	$0.021	$0.063	46.8
52	ANClaude Haiku 4.5	Oct 15, 2025	100%19 items	$1.25	$1	$5	46.5
53	ZAGLM-5.1	Apr 7, 2026	60%17 items	$0.26	$1.4	$4.4	45.7
54	MIMiniMax-M2.7	Mar 18, 2026	60%15 items	$0.06	$0.3	$1.2	42.5
55	TMInkling Small	Jul 30, 2026	80%21 items	Unverified	$0.45	$1.2	42.0

Not yet ranked

These models have partial scores and will receive a rank when evidence is complete.

View ranking requirements


MEMuse Wonder Full	63.6	Only one evaluation institution so far · Fewer than 3 coding evaluation types
MEMuse Wonder	61.0	Fewer than 3 coding evaluation types
XAGrok Voice 3.0	No score	Only one evaluation institution so far · Fewer than 3 coding evaluation types · Fewer than 2 reasoning evaluation types · Fewer than 2 professional-work evaluation types · Fewer than 2 knowledge and language evaluation types
IGGranite Switch 4.1 8B	No score	Only one evaluation institution so far · Fewer than 3 coding evaluation types · Fewer than 2 reasoning evaluation types · Fewer than 2 professional-work evaluation types · Fewer than 2 knowledge and language evaluation types
IGGranite Switch 4.1 30B	No score	Only one evaluation institution so far · Fewer than 3 coding evaluation types · Fewer than 2 reasoning evaluation types · Fewer than 2 professional-work evaluation types · Fewer than 2 knowledge and language evaluation types
NVNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16	No score	Only one evaluation institution so far · Fewer than 3 coding evaluation types · Fewer than 2 reasoning evaluation types · Fewer than 2 professional-work evaluation types · Fewer than 2 knowledge and language evaluation types
NVNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4	No score	Only one evaluation institution so far · Fewer than 3 coding evaluation types · Fewer than 2 reasoning evaluation types · Fewer than 2 professional-work evaluation types · Fewer than 2 knowledge and language evaluation types

Knowledge & language Text Model Leaderboard

Not yet ranked

Frequently asked questions

How does the Knowledge & language leaderboard differ from the overall leaderboard?

Why can a model have a score without a formal rank?

Should I choose a model using just one domain ranking?

What are the weights in the overall score?

How do raw evaluation results become an overall score?

What happens to the weights when a dimension has no results?

What evidence is required for a formal rank?