Bertrande

Best model that reads images

Which model should I use to analyse images?

As of 18 September 2026, the model ranking first for this question is Anthropic: Claude Opus 4.7 on OpenRouter, with intelligence index 55.0 and an output price of $25.00 per million tokens. Ranked by highest intelligence index, among models that accept image input, across 76 models for which we hold both figures. This ranking ignores speed and reliability: it is a query on price and a relayed capability score, not a verdict on which model serves you best.

How this ranking is built

Criterion: highest intelligence index, among models that accept image input. Only models whose published input modalities include images appear here. The capability comes from the provider's own catalogue.

This is a query, not an opinion. Both figures are shown on every row so you can check the order, and the table sorts on any column if you disagree with our criterion.

Two things to know before trusting this table. Capability scores are published by Artificial Analysis and relayed by the catalogue we read. They are not our measurement, and a score measures the model rather than the seller, so we apply it to every seller of that model. This ranking says nothing about speed or reliability, which we measure only in part: availability is published per upstream host in reliability.json and on the model pages, and we publish no latency at all, for reasons given on the data page. Prices are ours to observe, each carries the date we saw it, and we keep only the cheapest offer per model so that batch and free tiers do not crowd out the answer.

#ModelSellerIntelligence index/ 10040 of 40 heldScale from 3.8 to 55Input$ / 1M tokens40 of 40 heldScale from $0.0001 to $600Output$ / 1M tokens40 of 40 heldScale from $0.0001 to $600Contexttokens40 of 40 heldScale from 512 to 2MObserved
1Anthropic: Claude Opus 4.7OpenRouter55.0$5.00$25.001 000 00018 September 2026
2qwen/qwen3.8-maxNovita AI53.4$2.00$6.001 000 00017 September 2026
3Anthropic: Claude Fable 5.1OpenRouter53.4$10.00$50.001 000 00018 September 2026
4OpenAI: GPT-5.4OpenRouter53.1$2.50$15.001 050 00018 September 2026
5OpenAI: GPT-6 AstraOpenRouter52.8$10.00$50.001 050 00018 September 2026
6Anthropic: Claude Opus 5OpenRouter50.7$5.00$25.001 000 00018 September 2026
7Anthropic: Claude Fable 5OpenRouter49.7$10.00$50.001 000 00018 September 2026
8OpenAI: GPT-5.6 SolOpenRouter47.1$2.00$10.001 050 00018 September 2026
9Qwen: Qwen3.8 Max (0902)OpenRouter45.4$2.00$6.001 000 00016 September 2026
10SpaceXAI: Grok 4.6OpenRouter44.4$2.00$6.00500 00018 September 2026
11MoonshotAI: Kimi K3OpenRouter43.8$2.10$10.951 048 57618 September 2026
12OpenAI: GPT-5.6 TerraOpenRouter42.3$2.00$12.001 050 00018 September 2026
13Anthropic: Claude Opus 4.8OpenRouter42.0$5.00$25.001 000 00018 September 2026
14Z.ai: GLM 5.3 FlashOpenRouter41.9$0.090$0.3001 310 72018 September 2026
15Nex AGI: Nex-N2-ProOpenRouter41.7$0.250$1.00262 1448 September 2026
16Google: Gemini 3.8 FlashOpenRouter41.2$0.750$3.751 048 57618 September 2026
17SpaceXAI: Grok Build 0.1OpenRouter40.7$1.00$2.00256 00018 September 2026
18Qwen: Qwen3.6 PlusOpenRouter40.5$0.325$1.951 000 00018 September 2026
19Meta: Muse Spark 1.2OpenRouter39.8$1.25$4.251 048 57618 September 2026
20DeepSeek: DeepSeek V4.1 FlashOpenRouter39.5$0.150$0.6001 048 57618 September 2026
21Google: Gemini 3.7 FlashOpenRouter39.4$0.750$3.751 048 57618 September 2026
22SpaceXAI: Grok 4.5OpenRouter39.1$2.00$6.00500 00018 September 2026
23OpenAI: GPT-5.5OpenRouter38.6$5.00$30.001 050 00018 September 2026
24Anthropic: Claude Sonnet 5OpenRouter38.4$2.00$10.001 000 00018 September 2026
25OpenAI: GPT-5.6 LunaOpenRouter37.5$0.200$1.201 050 00018 September 2026
26OpenAI: GPT-5.1OpenRouter37.5$1.25$10.00400 00018 September 2026
27MoonshotAI: Kimi K2.5OpenRouter36.0$0.450$2.25262 14418 September 2026
28OpenAI: GPT-5OpenRouter35.3$1.25$10.00400 00018 September 2026
29Google: Gemini 3.6 FlashOpenRouter34.3$0.750$3.751 048 57618 September 2026
30Meta: Muse Spark 1.1OpenRouter34.3$1.25$4.251 048 57618 September 2026
31Qwen: Qwen3.8 27BOpenRouter33.9$0.214$2.551 000 00018 September 2026
32Google: Gemini 3.5 FlashOpenRouter33.0$1.50$9.001 048 57618 September 2026
33stepfun/step-3.7-flashNovita AI30.9$0.200$1.15262 14417 September 2026
34Anthropic: Claude Sonnet 4.6OpenRouter30.5$3.00$15.001 000 00018 September 2026
35Google: Gemini 3.1 Pro PreviewOpenRouter30.4$2.00$12.001 048 57618 September 2026
36Anthropic: Claude Sonnet 4OpenRouter29.8$3.00$15.001 000 00018 September 2026
37minimax/minimax-m3Novita AI29.6$0.300$1.201 000 00018 September 2026
38moonshotai/kimi-k2.6Novita AI27.5$0.800$3.40262 14418 September 2026
39MoonshotAI: Kimi K2.7 CodeOpenRouter26.3$0.7062$3.21262 14418 September 2026
40Google: Gemma 4 26B A4BOpenRouter26.1$0.090$0.300262 14418 September 2026

76 models meet this criterion. The table shows the first 40, so 36 ranked below the cut are not listed here; the full catalogue holds them all.

A model missing from this table is missing one of the two figures, not judged. We would rather show a shorter list than fill it with guesses.

Other questions we can answer this way