1. Models
  2. Kimi (Moonshot AI)
  3. Audio Language Model Benchmark Performance
Kimi (Moonshot AI)X · Apr 25, 2025 · official

Audio Language Model Benchmark Performance

Kimi (Moonshot AI)'s annotated chart drew 123K views on X: 0.5x its median post and #345 of 1,162 AI chart posts we hold by views. Read Oct 13, 2026.

Performance of audio language models across benchmarks

XDataAnnotated chartAll Kimi (Moonshot AI) modelsQwen2-AudioStep-AudioBaichuan-AudioQwen2.5-Omni
Published by Kimi (Moonshot AI) on X, Apr 25, 2025. Source: x.com
79/ 100

ViralChart score

Reached and resonated

More views and a higher engagement rate than the median post: it travelled and people acted on it.

#68 of 1,162 AI chart posts we hold · #10 of 20 Kimi (Moonshot AI) posts. Score = views 40%, likes 30%, engagement rate 15%, save rate 15%, each as a percentile of every AI chart post we hold.

Our read

The post sits in the Reached and resonated quadrant with a score rank of #68 of 1,162 AI chart posts.

Its 0.44% save rate sits at the 99th percentile among AI chart posts, 5.8x the 0.076% median.

The post scores 79, ranking #68 of 1,162 AI chart posts and #10 of 20 Kimi (Moonshot AI) posts.

Views reach 123K against a 226K company median, a 0.55x ratio and #14 of 20 Kimi (Moonshot AI) posts.

top 1%save rate

0.444% of viewers bookmarked it to come back to. The median post gets 0.076%.

5.4xthe median annotated chart post

Across 62 annotated chart posts we hold, the median gets 22.8K views.

top 20%engagement rate

1.14% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

0.34views per follower

123K views from an account with 365.4K followers.

Public X numbers from our read on Oct 13, 2026. Peers: 1,162 AI chart posts we hold and 20 from Kimi (Moonshot AI).

Where it sits

Reach against resonance

Each dot is a post. Right is more views, up is a higher engagement rate. The lines are the medians, so the four corners are the four kinds of post.

Among 1,162 AI chart posts we hold

Score #68 of 1,162

Views123K#345top 30%
Likes1.1K#250top 21%
Engagement rate1.14%#236top 20%
Save rate0.444%#8top 1%

Among 20 Kimi (Moonshot AI) posts

Score #10 of 20

Views123K#14bottom 33%
Likes1.1K#16bottom 23%
Engagement rate1.14%#5top 22%
Save rate0.444%#2top 7%

Growth

Our reads cover 3 days

Views123K
Age at our read536 days
Views per day of life229views divided by days since it was posted
Gained between our reads+2views over 3 days, about 1 a day now

Dots are our reads. The dotted line from the day it was posted to our first read is a gap, not data.

Kimi (Moonshot AI)'s posts over time

Every post from this account we hold, by date and views. This one is marked; the line is the running median of the last 10.

News · Apr 25, 2025

Kimi posts annotated audio language model benchmark chart

An annotated chart on audio language model benchmark performance drew 123K views and a 0.44% save rate on April 25, 2025.

What happened

Kimi (Moonshot AI) posted an annotated chart on audio language model benchmark performance on April 25, 2025. It was the account's only post that day.

The numbers

The post reached 123K views, ranking #345 of 1,162 AI chart posts. Its score of 79 ranks #68 of 1,162 AI chart posts and #10 of 20 Kimi (Moonshot AI) posts.

The lesson

A 0.44% save rate at the 99th percentile among AI chart posts shows readers kept this annotated chart at 5.8x the 0.076% median. The 5 models shown and 1 chart in the post sit alongside that top-decile save band.

What it means

At #14 of 20 Kimi (Moonshot AI) posts by views, this chart's 123K sits below the 226K company median. The #68 of 1,162 AI chart posts score rank shows the gap between its save performance and its view rank among this publisher's posts.

Written by ViralChart from public numbers read on Oct 13, 2026. Every number is checked against our data before it is shown.

Updates: what Kimi (Moonshot AI) posted next

  1. Kimi K2 benchmark results90.5K views
  2. Output Speed Comparison192.3K views
  3. AI Model Benchmark Performance Comparison641.7K views
  4. Kimi K2 Thinking vs GPT-5 vs Claude Sonnet4.9M views
  5. AI Model Benchmark Comparison7.4M views
  6. Kimi Code Bench258.9K views

Data and API

75 points read off this chart

Estimated from the image 70%
SeriesGroupValueRead
Kimi-AudioWenetSpeech94.2printed
Qwen2-AudioWenetSpeech97.4estimated
Baichuan-AudioWenetSpeech97.1estimated
StepAudioWenetSpeech97.1estimated
Qwen2.5-OmniWenetSpeech97.1estimated
Kimi-AudioAISHELL297.75printed
Qwen2-AudioAISHELL297.2printed
Baichuan-AudioAISHELL297.05printed
StepAudioAISHELL296.65printed
Qwen2.5-OmniAISHELL296.65printed
Kimi-AudioAISHELL199.4printed
Qwen2-AudioAISHELL199printed

Showing 12 of 75. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/b8898997d1ad.json
GET https://viral-chart.com/api/charts/b8898997d1ad.json
GET https://viral-chart.com/api/charts/b8898997d1ad.skill.md
Make one like thisOpen the post JSONChart data JSONSkill fileAPI docs

Static files in this prototype. The post JSON holds the public numbers, ranks, score, quadrant, our reads and, when checked, our copy.

API · Max

Use this chart via API

On the Max plan you can pull this chart's numbers with the provenance of each one, as JSON or CSV, with its redraw spec, or call it from an agent over MCP. Chart id b8898997d1ad.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/b8898997d1adTitle, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/b8898997d1ad/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/b8898997d1ad/render?view=1The draw-only view this page usesOpen
POST/mcpTool get_chart_data with this id, for Claude, Cursor and other agentsMax
curlMax
curl -s https://viral-chart.com/api/v1/charts/b8898997d1ad/data \
  -H "Authorization: Bearer $VIRALCHART_KEY"
Claude CodeMax
claude mcp add --transport http viralchart https://viral-chart.com/mcp \
  --header "Authorization: Bearer $VIRALCHART_KEY"

60 requests a minute per key; over that you get 429 with Retry-After. Up to 5 keys per account, made on your account page and shown once. Without Max, the data route answers 402 with a link to the plans. The numbers describe a chart its publisher owns, and every file carries a license note.

More from Kimi (Moonshot AI)

Kimi (Moonshot AI) grouped bar chart: AI model benchmark comparison11x
Kimi (Moonshot AI)·Apr 2026
AI model benchmark comparison
7.6M views17.9K likes0.3% eng.
Data
Kimi (Moonshot AI) grouped bar chart: AI model benchmark comparison9.7x
Kimi (Moonshot AI)·Jan 2026
AI model benchmark comparison
7.4M views15.6K likes0.3% eng.
Data
Kimi (Moonshot AI) grouped bar chart: AI model benchmark comparison8.6x
Kimi (Moonshot AI)·Jun 2026
AI model benchmark comparison
2.7M views13.9K likes0.6% eng.
Data
Kimi K2.7 Code and Kimi Code: AI Model Benchmark Comparison
OfficialX · Kimi (Moonshot AI)Jul 16, 2026
AI Model Benchmark Comparison25.6M views · 56.9K likes
Data
Kimi K2.7 Code and Kimi Code: Coding Benchmarks Comparison
OfficialX · Kimi (Moonshot AI)Jul 16, 2026
Coding Benchmarks Comparison25.6M views · 56.9K likes
Data
Kimi K2: Kimi K2 Thinking vs GPT-5 vs Claude Sonnet
OfficialX · Kimi (Moonshot AI)Nov 6, 2025
Kimi K2 Thinking vs GPT-5 vs Claude Sonnet4.9M views · 9.5K likes
Data
Kimi K2: Kimi Code Bench Performance vs Tokens
OfficialX · Kimi (Moonshot AI)Jun 12, 2026
Kimi Code Bench Performance vs Tokens2.7M views · 13.9K likes
Data
Kimi K3: AI Model Benchmarks Comparison
OfficialX · Kimi (Moonshot AI)Jul 16, 2026
AI Model Benchmarks Comparison357.6K views · 1.4K likes
Data
Kimi agent products and benchmarks: Vision RL Training Curves on Benchmarks
OfficialX · Kimi (Moonshot AI)Jan 30, 2026
Vision RL Training Curves on Benchmarks316.8K views · 1.9K likes
Data

Questions people ask

Where does this chart come from?

Kimi (Moonshot AI) published it on Apr 25, 2025 on X (x.com). We keep it here, with the publisher and date credited as text, so you can study it without leaving.

Can I make a chart like this?

Use the format, not the picture. Open its data page and use Make one like this: it starts from this chart's numbers and takes yours.