OpenHands Index

Name: OpenHands Index results
Creator: OpenHands Index
License: https://www.apache.org/licenses/LICENSE-2.0

Resolving front-end issues whose reports include screenshots.

Data older than 90 days: last updated 30 Jun 2026

Results dated: 30 Jun 2026
Models: 34
Unit: % resolved
Licence: Apache License 2.0

Front end (SWE-Bench Multimodal): MiniMax-M3

Top 15 of 34 results · % resolved, higher is better. Choose a model to highlight it.Clear highlight

1 Claude Fable 5Anthropic 70.6%
2 Claude Opus 4.8Anthropic 50.0%
3 Claude Opus 4.7Anthropic 48.5%
4 Gemini 3.1 Pro PreviewGoogle 44.1%
5 Claude Opus 4.6Anthropic 41.8%
6 Claude Opus 4.5Anthropic 41.2%
6 Kimi K2.6Moonshot AI 41.2%
6 GLM-5.1Z.ai 41.2%
9 Gemini 3.5 FlashGoogle 39.7%
10 GPT-5.5OpenAI 38.2%
11 Claude Sonnet 4.5Anthropic 36.8%
11 DeepSeek-V4-Pro (0423)DeepSeek 36.8%
11 Gemini 3 Pro PreviewGoogle 36.8%
11 MiniMax-M3MiniMax 36.8%
11 GPT-5.4OpenAI 36.8%

Full results

OpenHands Index: front end (SWE-Bench Multimodal), % resolved, higher is better
#	Model	Front end (SWE-Bench Multimodal) % resolved, higher is better	Price $ per million tokens, in / out
1	Claude Fable 5Anthropic	70.6%	$10 / $50
2	Claude Opus 4.8Anthropic	50.0%	$5 / $25
3	Claude Opus 4.7Anthropic	48.5%	$5 / $25
4	Gemini 3.1 Pro PreviewGoogle	44.1%	$2 / $12
5	Claude Opus 4.6Anthropic	41.8%	$5 / $25
6	Claude Opus 4.5Anthropic	41.2%	$5 / $25
6	Kimi K2.6Moonshot AI	41.2%	$0.95 / $4
6	GLM-5.1Z.ai	41.2%	$1.38 / $4.40
9	Gemini 3.5 FlashGoogle	39.7%	$1.50 / $9
10	GPT-5.5OpenAI	38.2%	$5 / $30
11	Claude Sonnet 4.5Anthropic	36.8%	$3 / $15
11	DeepSeek-V4-Pro (0423)DeepSeek	36.8%	$1.42 / $2.83
11	Gemini 3 Pro PreviewGoogle	36.8%	–
11	MiniMax-M3MiniMax	36.8%	$0.30 / $1.20
11	GPT-5.4OpenAI	36.8%	$2.50 / $15
16	GPT-5.2-CodexOpenAI	35.9%	$1.75 / $14
17	GLM-5Z.ai	35.3%	$0.95 / $2.55
18	Kimi K2.5Moonshot AI	32.8%	$0.57 / $2.85
19	Kimi K2 ThinkingMoonshot AI	32.4%	$0.60 / $2.50
20	Qwen3.6-PlusAlibaba	30.9%	$0.33 / $1.95
20	Qwen3-Coder-NextAlibaba	30.9%	$0.18 / $0.90
20	Claude Sonnet 4.6Anthropic	30.9%	$3 / $15
20	GPT-5.2OpenAI	30.9%	$1.75 / $14
24	Qwen3.5-FlashAlibaba	27.9%	$0.065 / $0.26
24	DeepSeek-V3.2 (reasoning on)DeepSeek	27.9%	$0.30 / $0.96
24	MiniMax-M2.7MiniMax	27.9%	$0.30 / $1.20
27	Trinity Large ThinkingArcee AI	25.0%	$0.25 / $0.80
27	MiniMax-M2.5MiniMax	25.0%	$0.30 / $1.20
29	Qwen3-Coder-480B-A35BAlibaba	23.5%	$0.35 / $1.50
30	Gemini 3 Flash PreviewGoogle	22.1%	$0.50 / $3
30	GLM-4.7Z.ai	22.1%	$0.54 / $1.98
32	Nemotron 3 Nano 30B A3BNVIDIA	20.9%	$0.05 / $0.20
33	Nemotron 3 Super 120B A12BNVIDIA	20.6%	$0.085 / $0.40
34	MiniMax-M2.1MiniMax	16.2%	$0.30 / $1.20

Swipe the table sideways for more columns.

Ranks follow the score as shown, so equal numbers share a rank. Results as published by OpenHands Index; we do not re-run them.

Progress over time

Front end (SWE-Bench Multimodal), plotted at each model's release date, higher is better. Each model counts once, at its best setting. Scores are today's, not launch day's; 1 model without a known release date is left off. Hover or tap a mark for its model.

Best score so far

Every model at its release date. The line moves each time a new release beats every earlier one, and each new best is named where there is room.

Best score by lab

Each lab's best so far, stepping whenever one of its releases beats its own earlier models. The 6 labs with the best scores today; 4 others not drawn.

AnthropicGoogleMoonshot AIZ.aiOpenAIDeepSeek

What it measures

Resolving front-end issues whose reports include screenshots.

What it does not measure

Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.

Source

OpenHands Index · Methodology

OpenHands Index by the OpenHands contributors, Apache License 2.0.