Guides · dev · mimo v2.6

MiMo, StepFun, and Hunyuan: cheap on the list, thin on evidence

Published 16 Oct 2026. Updated 16 Oct 2026. Researched 16 Oct 2026.

The big four labs get the long guides. These three are on the price table in volume enough to matter, and they do not yet have a direct-price file in the repo. Treat every percentage as an OpenRouter list price.

Entrant ids on the OpenRouter blend. OpenRouter list price, blended 75% input / 25% output. Snapshot 2026-10-16 05:20 UTC. Comparators resolve to Anthropic: Claude Opus 5.5 and OpenAI: GPT-6.1 Sol.
Model	Blended	vs Opus	vs Sol
mimo-v2.6-pro	$0.544	93% cheaper	86% cheaper
mimo-v2.6-flash	$0.175	98% cheaper	96% cheaper
step-3.5-flash	$0.150	98% cheaper	96% cheaper
hy3	$0.231	97% cheaper	94% cheaper

HY3 sits with the flash cluster. MiMo V2.6 Pro is a bit dearer and still far under the comparators on the blend. Step-3.5 Flash is among the lowest blends in the spotlight, with the caveat that StepFun has only a few rows. A lab with three ids is not a platform.

Preference votes

The LMArena coding snapshot includes mimo-v2.6-pro near the top cluster, ahead of several better-known Chinese ids, with a vote count you should read in the table before you believe the rank. Hunyuan’s preview row is much further down. StepFun does not appear in the names we kept for that chart. Missing means missing.

Style-controlled Bradley-Terry ratings from the LMArena leaderboard dataset. Not Elo. A higher rating means the model was preferred more often in blind votes. Intervals are the dataset's rating_lower and rating_upper. Ratings are rounded to 1 decimal for display in the chart; full values are stored. Category: coding. Published 2026-10-15, fetched 2026-10-16. Source: https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset (text_style_control, latest).
Entry	rating	Detail
Claude Opus 5.5 (High)	1547.52	rank 6, 1,894 votes, 1533.61–1561.44
gpt-6.1-sol-max	1539.79	rank 10, 1,257 votes, 1522.63–1556.95
Kimi K3 (Max)	1537.83	rank 12, 8,306 votes, 1530.58–1545.09
mimo-v2.6-pro	1537.58	rank 13, 1,105 votes, 1519.93–1555.23
glm-5.3-flash	1524.53	rank 27, 8,457 votes, 1517.07–1531.99
deepseek-v4.1-flash-max	1523.37	rank 29, 3,527 votes, 1513.1–1533.65
qwen3.8-max	1523.36	rank 30, 7,677 votes, 1515.79–1530.93
glm-5.3-max	1518.51	rank 38, 5,400 votes, 1509.88–1527.13
kimi-k2.6	1516.03	rank 44, 11,091 votes, 1509.15–1522.92
mimo-v2.6-flash	1512.93	rank 51, 2,625 votes, 1500.97–1524.89
deepseek-v4-pro	1500.58	rank 78, 17,136 votes, 1494.66–1506.51
qwen3.8-27b	1499.13	rank 81, 6,417 votes, 1491.03–1507.23
minimax-m3	1496.69	rank 87, 18,242 votes, 1490.99–1502.39
deepseek-v4-flash	1484.16	rank 105, 15,288 votes, 1477.95–1490.37
hunyuan-hy3-preview	1452.74	rank 153, 2,055 votes, 1439.33–1466.16

SWE-bench Verified, in our extract, has no MiMo, StepFun, or HY3 row. The Qwen-coder and GLM rows on that chart are other labs.

How we would try them

Call the OpenRouter id for a task you already run on a flash model. Compare the trace, not the rank. Do not build a company workflow on MiMo until someone has read a Xiaomi or host data-processing page. We have not. The provider notes say that in shorter form.

Related: which model, price map.

Questions

Is MiMo worth trying?

On price and on the LMArena coding snapshot, MiMo V2.6 Pro is interesting. We did not verify a Xiaomi invoice or a SWE-bench score.

Is Hunyuan HY3 the cheapest Hunyuan?

No. The translation models are cheaper and they are not general chat models. HY3 is the one in the flash comparison.

Sources

OpenRouter models API, accessed 2026-10-16
LMArena leaderboard dataset, accessed 2026-10-16
SWE-bench leaderboards.json, accessed 2026-10-16