Model Rankings

Models ranked by composite utility score across all benchmark-backed use cases. The score weights each use-case result by its confidence level, so models with broader, higher-confidence coverage rank higher.

How the score works

Utility Score = sum of (use-case score × confidence) / sum of (confidence) across all scored use cases. This means a model that scores well on many use cases with high confidence ranks above one that scores well on few. Coverage breadth is used as a tiebreaker.

Recent Changes

0 use cases changed their #1 model since the last scoring update. Currently 19,299 model-use case pairings scored.

Showing top 100 models

Rank	Model	Utility Score	Use Cases	Avg Confidence	Verticals	Evidence	Profile
#1	gemini-3-pro-preview external/google/gemini-3-pro-preview	24.8%	141 (98.6%)	27.2%	24	3,226	View
#2	gemini-2.5-pro external/google/gemini-2-5-pro	23.6%	143 (100.0%)	33.4%	24	3,520	View
#3	gpt-4.1-20250414 external/openai/gpt-4-1-20250414	21.4%	143 (100.0%)	29.3%	24	2,935	View
#4	anthropic/claude-sonnet-4.6 external/anthropic/claude-sonnet-4-6	20.5%	126 (88.1%)	22.8%	22	2,221	View
#5	Grok-4-0709 external/xai/grok-4-0709	20.2%	143 (100.0%)	26.0%	24	2,846	View
#6	Arch-Agent-32B katanemo/Arch-Agent-32B	19.0%	11 (7.7%)	33.7%	4	44	View
#7	gpt-5-mini-2025-08-07 external/openai/gpt-5-mini-2025-08-07	18.9%	135 (94.4%)	23.2%	24	2,548	View
#8	google/gemini-3.1-pro-preview external/google/gemini-3-1-pro-preview	18.5%	134 (93.7%)	19.2%	24	2,373	View
#9	gpt-5-2025-08-07 external/openai/gpt-5-2025-08-07	18.5%	134 (93.7%)	20.2%	24	2,325	View
#10	openai/gpt-5.4-2026-03-05 external/openai/gpt-5-4-2026-03-05	18.3%	124 (86.7%)	19.2%	23	2,089	View
#11	claude-sonnet-4-20250514 external/anthropic/claude-sonnet-4-20250514	17.3%	141 (98.6%)	23.9%	24	2,598	View
#12	gemini-2.5-flash external/google/gemini-2-5-flash	17.2%	135 (94.4%)	22.7%	24	2,134	View
#13	gpt-5.1-2025-11-13 external/openai/gpt-5-1-2025-11-13	16.4%	126 (88.1%)	20.3%	23	2,173	View
#14	claude-opus-4-5-20251101 external/anthropic/claude-opus-4-5-20251101	16.4%	126 (88.1%)	20.0%	23	2,151	View
#15	gemini-3-flash-preview external/google/gemini-3-flash-preview	15.7%	121 (84.6%)	19.1%	23	2,043	View
#16	gpt-5.2-2025-12-11 external/openai/gpt-5-2-2025-12-11	15.6%	108 (75.5%)	15.8%	21	1,559	View
#17	anthropic/claude-opus-4-6-thinking external/anthropic/claude-opus-4-6-thinking	15.5%	108 (75.5%)	15.8%	21	1,559	View
#18	google/gemini-3.1-flash-lite-preview external/google/gemini-3-1-flash-lite-preview	15.3%	112 (78.3%)	19.4%	22	1,796	View
#19	xai-org/grok-4-fast-reasoning external/xai-org/grok-4-fast-reasoning	15.2%	125 (87.4%)	20.2%	22	2,146	View
#20	falcon-7b-instruct tiiuae/falcon-7b-instruct	15.1%	13 (9.1%)	19.8%	3	49	View
#21	Llama-2-7b-chat-hf meta-llama/Llama-2-7b-chat-hf	15.0%	27 (18.9%)	17.2%	8	109	View
#22	anthropic/claude-opus-4-5-20251101-thinking external/anthropic/claude-opus-4-5-20251101-thinking	14.7%	108 (75.5%)	15.8%	21	1,559	View
#23	gpt-4o external/openai/gpt-4o	14.6%	104 (72.7%)	17.5%	23	1,286	View
#24	xai-org/grok-4-1-fast-reasoning external/xai-org/grok-4-1-fast-reasoning	14.5%	125 (87.4%)	20.2%	22	2,146	View
#25	kimi/kimi-k2.5-thinking external/kimi/kimi-k2-5-thinking	14.0%	130 (90.9%)	18.8%	24	2,210	View
#26	Arch-Agent-3B katanemo/Arch-Agent-3B	13.6%	11 (7.7%)	33.7%	4	44	View
#27	anthropic/claude-sonnet-4-5-20250929-thinking external/anthropic/claude-sonnet-4-5-20250929-thinking	13.6%	108 (75.5%)	15.8%	21	1,559	View
#28	qwen-2.5-72b-instruct external/qwen/qwen-2-5-72b-instruct	13.4%	135 (94.4%)	18.3%	23	1,461	View
#29	Arch-Agent-1.5B katanemo/Arch-Agent-1.5B	13.2%	11 (7.7%)	33.7%	4	44	View
#30	gpt-4.1-mini-20250414 external/openai/gpt-4-1-mini-20250414	12.7%	122 (85.3%)	16.8%	23	1,456	View
#31	zephyr-7b-beta HuggingFaceH4/zephyr-7b-beta	12.6%	22 (15.4%)	17.5%	6	98	View
#32	c4ai-command-r-plus CohereLabs/c4ai-command-r-plus	12.3%	16 (11.2%)	17.7%	5	73	View
#33	Kimi-VL-A3B-Instruct EasyDeL/Kimi-VL-A3B-Instruct	12.2%	26 (18.2%)	14.0%	12	146	View
#34	Kimi K2 Thinking external/kimi/kimi-k2-thinking	12.1%	104 (72.7%)	19.1%	20	1,527	View
#35	GLM-5 Laibaaaaa/GLM-5	12.0%	6 (4.2%)	12.8%	2	29	View
#36	Ovis1.6-Gemma2-9B AIDC-AI/Ovis1.6-Gemma2-9B	12.0%	18 (12.6%)	14.1%	9	90	View
#37	alibaba/qwen3.5-flash external/alibaba/qwen3-5-flash	12.0%	100 (69.9%)	15.5%	20	1,355	View
#38	gemma-2b-it google/gemma-2b-it	12.0%	27 (18.9%)	17.2%	8	109	View
#39	gemma-7b-it google/gemma-7b-it	11.8%	35 (24.5%)	16.6%	9	173	View
#40	gemma-2-27b-it google/gemma-2-27b-it	11.8%	25 (17.5%)	17.4%	5	180	View
#41	gpt-oss-120b openai/gpt-oss-120b	11.7%	8 (5.6%)	15.0%	2	33	View
#42	x-ai/grok-3 external/x-ai/grok-3	11.7%	109 (76.2%)	15.4%	22	1,375	View
#43	anthropic/claude-haiku-4-5-20251001-thinking external/anthropic/claude-haiku-4-5-20251001-thinking	11.7%	108 (75.5%)	15.8%	21	1,559	View
#44	z-ai/glm-4.7 external/z-ai/glm-4-7	11.5%	112 (78.3%)	16.4%	21	1,650	View
#45	minimax/minimax-m2.1 external/minimax/minimax-m2-1	11.4%	116 (81.1%)	17.7%	21	1,786	View
#46	mistralai/mistral-large-2512 external/mistralai/mistral-large-2512	11.3%	108 (75.5%)	19.0%	21	1,631	View
#47	o3-20250416 external/openai/o3-20250416	11.3%	106 (74.1%)	16.5%	21	1,545	View
#48	gpt-4o-2024-08-06 external/openai/gpt-4o-2024-08-06	11.2%	140 (97.9%)	23.3%	24	2,284	View
#49	mistralai-Mistral-Nemo-Instruct-2407 grimjim/mistralai-Mistral-Nemo-Instruct-2407	11.2%	13 (9.1%)	15.9%	4	50	View
#50	Qwen3-1.7B-FC contextboxai/Qwen3-1.7B-FC	11.1%	11 (7.7%)	33.7%	4	44	View
#51	11 Yura37/11	11.0%	3 (2.1%)	11.5%	2	6	View
#52	openai/gpt-5 external/openai/gpt-5	11.0%	108 (75.5%)	15.3%	21	1,055	View
#53	alpaca-native maicomputer/alpaca-native	11.0%	13 (9.1%)	19.8%	3	49	View
#54	gpt-oss-20b openai/gpt-oss-20b	10.9%	6 (4.2%)	14.5%	1	12	View
#55	xai-org/grok-4-1-fast-non-reasoning external/xai-org/grok-4-1-fast-non-reasoning	10.7%	121 (84.6%)	19.5%	22	1,965	View
#56	Llama-3.3-70B-Instruct meta-llama/Llama-3.3-70B-Instruct	10.6%	24 (16.8%)	14.7%	10	118	View
#57	GLM-4.6V EasyDeL/GLM-4.6V	10.5%	2 (1.4%)	11.3%	1	4	View
#58	anthropic/claude-opus-4-1-20250805 external/anthropic/claude-opus-4-1-20250805	10.5%	100 (69.9%)	17.6%	20	1,372	View
#59	Meta-Llama-3-8B-Instruct meta-llama/Meta-Llama-3-8B-Instruct	10.4%	52 (36.4%)	16.3%	13	318	View
#60	grok4 CometAPI/grok4	10.4%	9 (6.3%)	14.9%	3	45	View
#61	gpt-4o-20241120 external/openai/gpt-4o-20241120	10.4%	106 (74.1%)	15.9%	21	1,278	View
#62	gpt-4o-2024-05-13 external/openai/gpt-4o-2024-05-13	10.3%	102 (71.3%)	14.9%	22	856	View
#63	Kimi-K2-Instruct unsloth/Kimi-K2-Instruct	10.2%	10 (7.0%)	12.2%	4	29	View
#64	deepseek/deepseek-r1 external/deepseek/deepseek-r1	10.1%	112 (78.3%)	17.7%	21	1,709	View
#65	qwen/qwen3-max external/qwen/qwen3-max	10.1%	102 (71.3%)	14.9%	22	1,214	View
#66	Mistral-Small-24B-Instruct-2501 RedHatAI/Mistral-Small-24B-Instruct-2501	10.0%	9 (6.3%)	13.4%	3	30	View
#67	gemma-3-27b-it mcrovero/gemma-3-27b-it	9.9%	101 (70.6%)	13.8%	22	950	View
#68	Qwen2.5-32B-Instruct Qwen/Qwen2.5-32B-Instruct	9.9%	1 (0.7%)	10.9%	1	3	View
#69	c4ai-command-r-plus-08-2024 CohereLabs/c4ai-command-r-plus-08-2024	9.8%	11 (7.7%)	15.3%	3	33	View
#70	Qwen2.5-Coder-7B Qwen/Qwen2.5-Coder-7B	9.8%	6 (4.2%)	14.5%	1	12	View
#71	Llama-3.1-70B-Instruct meta-llama/Llama-3.1-70B-Instruct	9.7%	24 (16.8%)	17.8%	10	137	View
#72	Qwen3-Embedding-8B anyidea/Qwen3-Embedding-8B	9.6%	24 (16.8%)	12.5%	6	143	View
#73	gemma-2-9b-it google/gemma-2-9b-it	9.5%	19 (13.3%)	15.0%	4	106	View
#74	Mistral-7B-OpenOrca Open-Orca/Mistral-7B-OpenOrca	9.5%	18 (12.6%)	18.7%	4	77	View
#75	Qwen3-Embedding-4B Qwen/Qwen3-Embedding-4B	9.5%	24 (16.8%)	12.5%	6	143	View
#76	GLM-4.5-Air anas125244235/GLM-4.5-Air	9.4%	10 (7.0%)	12.2%	4	29	View
#77	Meta-Llama-3-70B-Instruct meta-llama/Meta-Llama-3-70B-Instruct	9.3%	11 (7.7%)	12.8%	4	42	View
#78	Qwen3-32B Qwen/Qwen3-32B	9.1%	8 (5.6%)	15.0%	2	33	View
#79	Euler-Legal-Embedding-V1 Mira190/Euler-Legal-Embedding-V1	9.1%	24 (16.8%)	12.5%	6	143	View
#80	DeepSeek-V2.5 deepseek-ai/DeepSeek-V2.5	8.9%	7 (4.9%)	13.0%	2	26	View
#81	openai/gpt-4o-mini-2024-07-18 external/openai/gpt-4o-mini-2024-07-18	8.9%	143 (100.0%)	20.2%	24	1,874	View
#82	Mistral-7B-Instruct-v0.2 mistralai/Mistral-7B-Instruct-v0.2	8.7%	2 (1.4%)	13.4%	1	6	View
#83	QwQ-32B-Preview Qwen/QwQ-32B-Preview	8.6%	6 (4.2%)	14.9%	1	18	View
#84	Phi-3-medium-128k-instruct microsoft/Phi-3-medium-128k-instruct	8.6%	9 (6.3%)	14.1%	2	27	View
#85	Qwen3-Embedding-0.6B 1kxia/Qwen3-Embedding-0.6B	8.6%	24 (16.8%)	12.5%	6	143	View
#86	baseline yokoe/baseline	8.5%	3 (2.1%)	11.5%	2	6	View
#87	xai-org/grok-4-fast-non-reasoning external/xai-org/grok-4-fast-non-reasoning	8.5%	109 (76.2%)	15.6%	22	1,484	View
#88	phi-4 microsoft/phi-4	8.4%	57 (39.9%)	14.2%	16	405	View
#89	Qwen3-2B raydel-0307/Qwen3-2B	8.3%	12 (8.4%)	14.4%	7	73	View
#90	o3-pro CometAPI/o3-pro	8.2%	3 (2.1%)	10.4%	2	11	View
#91	o4-mini-20250416 external/openai/o4-mini-20250416	8.1%	107 (74.8%)	16.4%	22	1,560	View
#92	Qwen-VL-Chat Qwen/Qwen-VL-Chat	8.0%	18 (12.6%)	14.1%	9	90	View
#93	BOOM_4B_v1 ICT-TIME-and-Querit/BOOM_4B_v1	8.0%	24 (16.8%)	12.5%	6	143	View
#94	gte-Qwen2-1.5B-instruct Alibaba-NLP/gte-Qwen2-1.5B-instruct	8.0%	24 (16.8%)	12.5%	6	143	View
#95	Nemotron-3-Nano-30B-A3B unsloth/Nemotron-3-Nano-30B-A3B	7.9%	8 (5.6%)	12.9%	4	49	View
#96	GritLM-7B GritLM/GritLM-7B	7.9%	24 (16.8%)	12.5%	6	143	View
#97	Qwen2.5-14B-Instruct Qwen/Qwen2.5-14B-Instruct	7.9%	1 (0.7%)	10.9%	1	3	View
#98	GritLM-8x7B GritLM/GritLM-8x7B	7.8%	24 (16.8%)	12.5%	6	143	View
#99	gemma-3-12b residuals/gemma-3-12b	7.7%	18 (12.6%)	14.1%	9	90	View
#100	Kimi-K2-Instruct-0905 moonshotai/Kimi-K2-Instruct-0905	7.6%	3 (2.1%)	10.2%	2	12	View