- Giants
- Artificial Analysis
- GPU throughput vs speed

GPU throughput vs speed
Artificial Analysis's line chart drew 2.6K views on X: 0.0x its typical post and #125 of 127 Artificial Analysis charts we track by views. Read Oct 14, 2026.
On GLM-5.2/5.3, MI355X lands between Hopper and Blackwell. At 100 tok/s per user it serves ~26M tokens/s per MW, ahead of H200 (~16M) but behind B200 (~42M) and B300 (~44M), and its single-agent speed matches H200 at 228 tok/s, against 312
On GLM-5.2/5.3, MI355X lands between Hopper and Blackwell. At 100 tok/s per user it serves ~26M tokens/s per MW, ahead of H200 (~16M) but behind B200 (~42M) and B300 (~44M), and its single-agent speed matches H200 at 228
Make it yours
We have not read this chart's numbers yet
Its own maker appears here once its numbers are read. Until then, these are other real charts in a similar format: each data page starts from that chart's numbers and takes yours.
API
Not in the API yet
We have not read this chart's numbers yet, so the API has nothing to return for it. Charts with numbers read are on the data page, and each one can be called by id.
More from Artificial Analysis
All 127GPT-5.6 Sol and Luna are ahead of Terra at every point on the Intelligence vs Cost per Task chart. GPT-5.6 Luna stands out as a particularly cost efficient model Charting the Artificial Analysis Intelligence Index shows
Artificial Analysis·Jul 2026DeepSeek takes the lead: DeepSeek V3-0324 is now the highest scoring non-reasoning model This is the first time an open weights model is the leading non-reasoning model, a milestone for open source. DeepSeek V3-0324 ha
Artificial Analysis·Mar 2025MiMo-V2.6-Pro debuts as the top open weights model on the Artificial Analysis Intelligence Index (46). At $0.13 per Intelligence Index task, it lands on the Intelligence vs. Cost per Task Pareto frontier @Xiaomi has jus
Artificial Analysis·Sep 2026Announcing Artificial Analysis State of AI: China 🇨🇳 For the first time, we are charting the rise of China’s top AI companies to the AI frontier. In this benchmarking report, we map the Chinese AI ecosystem and prese
Artificial Analysis·Feb 2025xAI has released Grok 4 Fast - breaking through our intelligence vs cost frontier by achieving Gemini 2.5 Pro level intelligence at a ~25X cheaper cost Intelligence: @xai shared with us pre-release access to Grok 4 Fast
Artificial Analysis·Sep 2025Anthropic has launched Claude Sonnet 5.5: it scores 56 on the Artificial Analysis Intelligence Index, just 2 points behind Opus 5.5 (max), but at the highest Output Tokens per Task we’ve seen With max effort, Sonnet 5.5
Artificial Analysis·Sep 2026Other giants using a line chart
All 315NEW 🧵: Is human intelligence starting to decline? Recent results from major international tests show that the average person’s capacity to process information, use reasoning and solve novel problems has been falling si
Financial Times·Mar 2025Every three years the OECD, a club of mostly rich countries, releases the results of international school tests sat by 15-year-olds all across the world. Anyone who cares about the young of today should be alarmed at thi
The Economist·Sep 2026AI is getting cheaper more quickly than any other transformative tech in history. At a given level of performance, cost has fallen ~47%/quarter since 2023. That’s 4× faster than DNA sequencing, 6× faster than compute, 1
Epoch AI·Sep 2026Two extraordinary charts from today’s PISA test results: 1) School test scores continue to collapse internationally, underscoring how this is no longer a Covid effect but sustained decline. Those falls in reading and m
Financial Times·Sep 2026NEW: Progressives have a birth rate problem For all the talk of a general fall in births, the drop is overwhelmingly driven by people on the left having fewer kids. By ceding the topic of family and children to the rig
Financial Times·Aug 2025NEW: updated long-run gap in voting between young men and women in Germany: The gender gap continues to widen, but contrary to what is often assumed, young men continue to vote roughly in line with the overall populatio
Financial Times·Feb 2025Questions people ask
How far did Artificial Analysis's "GPU throughput vs speed" chart travel?
2,573 views, 2 likes, 0 reposts and 0 saves on X, read Oct 14, 2026. A normal post from @ArtificialAnlys gets about 52.9K views.
What kind of chart is it?
A line chart. Throughput per MW declines as output speed increases across models.
Can I use Artificial Analysis's chart?
Use the format, not the picture. The chart, logo and design belong to Artificial Analysis. ViralChart redraws the chart type with your numbers and words, and credits the original publisher.