LLM benchmarks

Name: Respan
Availability: InStock

Every model's score on every benchmark we track, each linked to where it was published. Independent runs are listed apart from the numbers labs report for their own models. Many of them feed the Respan Index.

LLM benchmarks

Respan IndexCodingAgentsReasoningMathKnowledgeMultimodalArenaOther

Respan Index

Models ranked on one 0 to 100 score from public benchmarks and lab results.

Model		Respan Index	Coding	Agents	Reasoning	Knowledge	Preference
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.

Model		Respan Index	Coding	Agents	Reasoning	Knowledge	Preference
1.	Claude Opus 5.5by Anthropic	72.7	72.5	78.7	75.3	70.4	60.4
2.	Gemini 4 Argonby Google	71.4	64.4	80.2	78.4	70.1*	57.3
3.	GPT-6 Astraby OpenAI	70.7	61.9	77.7	77.0	75.6	59.6
4.	GPT-6.1 Solby OpenAI	69.7	61.2	73.7	78.5	74.5	59.0
5.	Claude Fable 5.1by Anthropic	69.2	69.5	73.4	70.2	71.5	58.8
6.	Claude Sonnet 5.5by Anthropic	68.3	69.9	77.7	70.5	48.6	59.3
7.	Muse Wonderby Meta	66.9	58.3	78.7*	72.0	58.1	59.1*
8.	Claude Opus 5by Anthropic	63.9	61.1	70.5	65.2	61.1	57.5
9.	GPT-6 Solby OpenAI	63.1	52.7	72.4	68.6	60.6	57.2
10.	Claude Fable 5by Anthropic	62.2	57.3	68.4	60.6	72.4	56.1
11.	GPT-5.6 Solby OpenAI	60.8	45.2	68.6	67.2	69.5	57.1
12.	MiMo-V2.6-Proby Xiaomi MiMo	56.8	46.0	65.6	59.2	57.5*	55.8
13.	Claude Haiku 5.5by Anthropic	54.4	50.0	69.3	55.8	23.6	54.9
14.	GPT-5.6 Terraby OpenAI	53.7	38.7	63.4	62.3	44.7	54.4
15.	Step 5 Previewby StepFun	53.6	45.6	57.6	56.5*	55.1*	54.2
16.	Muse Spark 1.3by Meta	53.4	40.5	65.2	49.0	61.9	56.7
17.	MiMo-V2.6-Flashby Xiaomi MiMo	52.9	40.6	62.8	53.1	54.2*	55.9
18.	Gemini 3.8 Flashby Google	52.7	37.3	67.2	44.8	70.9	55.0
19.	GPT-5.5by OpenAI	52.5	28.7	64.0	57.9	63.7	56.7
20.	Claude Opus 4.8by Anthropic	52.1	35.3	64.3	55.2	52.5	54.3
21.	Grok 4.6by xAI	51.1	33.8	65.3	51.4	51.1	55.5
22.	Kimi K3by Moonshot AI	50.3	37.2	62.2	46.7	52.9	56.6
22.	Qwen3.8-Maxby Qwen	50.3	38.8	68.5	40.5	48.2	57.1
24.	DeepSeek V4.1 Flashby DeepSeek	50.1	40.1	59.2	46.9	51.6	55.6
25.	Grok 4.7by xAI	49.7	43.6	65.2	34.3	55.6	55.9

Model		Respan Index	Coding	Agents	Reasoning	Knowledge	Preference
1.	Claude Opus 5.5by Anthropic	72.7	72.5	78.7	75.3	70.4	60.4
2.	Gemini 4 Argonby Google	71.4	64.4	80.2	78.4	70.1*	57.3
3.	GPT-6 Astraby OpenAI	70.7	61.9	77.7	77.0	75.6	59.6
4.	GPT-6.1 Solby OpenAI	69.7	61.2	73.7	78.5	74.5	59.0
5.	Claude Fable 5.1by Anthropic	69.2	69.5	73.4	70.2	71.5	58.8
6.	Claude Sonnet 5.5by Anthropic	68.3	69.9	77.7	70.5	48.6	59.3
7.	Muse Wonderby Meta	66.9	58.3	78.7*	72.0	58.1	59.1*
8.	Claude Opus 5by Anthropic	63.9	61.1	70.5	65.2	61.1	57.5
9.	GPT-6 Solby OpenAI	63.1	52.7	72.4	68.6	60.6	57.2
10.	Claude Fable 5by Anthropic	62.2	57.3	68.4	60.6	72.4	56.1
11.	GPT-5.6 Solby OpenAI	60.8	45.2	68.6	67.2	69.5	57.1
12.	MiMo-V2.6-Proby Xiaomi MiMo	56.8	46.0	65.6	59.2	57.5*	55.8
13.	Claude Haiku 5.5by Anthropic	54.4	50.0	69.3	55.8	23.6	54.9
14.	GPT-5.6 Terraby OpenAI	53.7	38.7	63.4	62.3	44.7	54.4
15.	Step 5 Previewby StepFun	53.6	45.6	57.6	56.5*	55.1*	54.2
16.	Muse Spark 1.3by Meta	53.4	40.5	65.2	49.0	61.9	56.7
17.	MiMo-V2.6-Flashby Xiaomi MiMo	52.9	40.6	62.8	53.1	54.2*	55.9
18.	Gemini 3.8 Flashby Google	52.7	37.3	67.2	44.8	70.9	55.0
19.	GPT-5.5by OpenAI	52.5	28.7	64.0	57.9	63.7	56.7
20.	Claude Opus 4.8by Anthropic	52.1	35.3	64.3	55.2	52.5	54.3
21.	Grok 4.6by xAI	51.1	33.8	65.3	51.4	51.1	55.5
22.	Kimi K3by Moonshot AI	50.3	37.2	62.2	46.7	52.9	56.6
22.	Qwen3.8-Maxby Qwen	50.3	38.8	68.5	40.5	48.2	57.1
24.	DeepSeek V4.1 Flashby DeepSeek	50.1	40.1	59.2	46.9	51.6	55.6
25.	Grok 4.7by xAI	49.7	43.6	65.2	34.3	55.6	55.9

LLM benchmarks

LLM benchmarks

Respan Index

LLM benchmarks

Respan Index

LMArena Elo

Built for AI agents.
Break less.
Ship more.

LLM benchmarks

LLM benchmarks

Respan Index

LMArena Elo

Built for AI agents.
Break less.
Ship more.

Respan Index

LMArena Elo

Built for AI agents. Break less. Ship more.

Respan Index

LMArena Elo

Built for AI agents. Break less. Ship more.

Built for AI agents.
Break less.
Ship more.

Built for AI agents.
Break less.
Ship more.