Pairwise benchmark snapshot · Aug 1, 2026
In this head-to-head showdown, Claude Sonnet 4 delivers higher overall intelligence and human-preferred responses (Elo 1,455 vs 1,430), while Claude Sonnet 4 leads in SWE-bench software engineering benchmarks (62.8%), while Yi-Large is more budget-friendly at $0.3/1M per 1M output tokens, while Claude Sonnet 4 provides faster response streaming (92 tok/s). Review the complete breakdown below to determine which model best fits your performance and budget requirements.
9 direct benchmark disciplines evaluated across capability, speed, and cost
First Sonnet 4 generation. Bridge between 3.5/3.7 and Sonnet 5.
01.AI full-scale dense model for complex instruction following.
Δ 25 Arena Elo pts
92 tok/s
$0.3 / 1M output
Relative percentile scores computed across all active models in the benchmark catalog.
Comparing top Western standard models with China's leading frontier rival across 6 skill dimensions. Tap any spoke or dot to inspect.
Category wins across reasoning intelligence, generation speed, and token cost.
Preference Elo, Coding proficiency, SWE-bench & LiveBench accuracy
Generation throughput and time to first token responsiveness
Cost per million tokens and max context window length
| Benchmark | Claude Sonnet 4 | Yi-Large | Advantage Delta |
|---|---|---|---|
| Preference Elo | +25 | ||
| Coding Elo | +58 | ||
| LiveBench | +2.7% | ||
| SWE-bench | +9% | ||
| GPQA Diamond | +4% | ||
| Time to first token | — | ||
| Output speed | 92 tok/s | 90 tok/s | +2 tok/s |
| Input price | $0.3/1M | +$2.7/1M | |
| Output price | $0.3/1M | +$14.7/1M | |
| Context window | +167k |
Simulate monthly production API costs in USD (US Dollar).
Yi-Large is estimated to save $315.00/month ($3,780/year).
Higher SWE-bench (62.8%).
Lower output list price ($0.3/1M).
Lower TTFT (220 ms).
Larger window (200k).
Claude Sonnet 4 is the side marked multimodal in the catalog.
| Target Workload | Recommended Pick | Evaluation Rationale |
|---|---|---|
| Repo / coding agents | Claude Sonnet 4 | Higher SWE-bench (62.8%). |
| High-volume chat | Yi-Large | Lower output list price ($0.3/1M). |
| Voice / low-latency UI | Claude Sonnet 4 | Lower TTFT (220 ms). |
| Long-document RAG | Claude Sonnet 4 | Larger window (200k). |
| Screenshots / vision | Claude Sonnet 4 | Claude Sonnet 4 is the side marked multimodal in the catalog. |
No comments posted on this matchup yet. Be the first to share an evaluation note!
Dynamic OpenGraph banner generated at /compare/claude-sonnet-4-vs-yi-large/opengraph-image
Verified Head-to-Head Telemetry