Pairwise benchmark snapshot · Aug 1, 2026
In this head-to-head showdown, Doubao Pro 1.5 delivers higher overall intelligence and human-preferred responses (Elo 1,470 vs 1,358), while DeepSeek R1 leads in SWE-bench software engineering benchmarks (65.2%), while Doubao Pro 1.5 is more budget-friendly at $0.28/1M per 1M output tokens. Review the complete breakdown below to determine which model best fits your performance and budget requirements.
8 direct benchmark disciplines evaluated across capability, speed, and cost
Open-weights reasoning model trained with large-scale RL.
ByteDance flagship enterprise model with ultra-low token cost and 128k context.
Simulate accuracy gains vs added response time & token cost
Reasoning models “think before answering” by generating internal reasoning tokens. Higher effort improves math, coding, and logic accuracy, but increases response delay and token costs.
Δ 112 Arena Elo pts
105 tok/s
$0.28 / 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 | DeepSeek R1 | Doubao Pro 1.5 | Advantage Delta |
|---|---|---|---|
| Preference Elo | +112 | ||
| Coding Elo | — | — | |
| LiveBench | +5% | ||
| SWE-bench | +3.1% | ||
| GPQA Diamond | +2.3% | ||
| Time to first token | +230 ms | ||
| Output speed | 62 tok/s | 105 tok/s | +43 tok/s |
| Input price | $0.55/1M | $0.11/1M | +$0.44/1M |
| Output price | $2.19/1M | $0.28/1M | +$1.91/1M |
| Context window | — |
Simulate monthly production API costs in USD (US Dollar).
Doubao Pro 1.5 is estimated to save $44.05/month ($529/year).
Higher SWE-bench (65.2%).
Lower output list price ($0.28/1M).
Lower TTFT (190 ms).
Larger window (128k).
Doubao Pro 1.5 is the side marked multimodal in the catalog.
| Target Workload | Recommended Pick | Evaluation Rationale |
|---|---|---|
| Repo / coding agents | DeepSeek R1 | Higher SWE-bench (65.2%). |
| High-volume chat | Doubao Pro 1.5 | Lower output list price ($0.28/1M). |
| Voice / low-latency UI | Doubao Pro 1.5 | Lower TTFT (190 ms). |
| Long-document RAG | DeepSeek R1 | Larger window (128k). |
| Screenshots / vision | Doubao Pro 1.5 | Doubao Pro 1.5 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/deepseek-r1-vs-doubao-1-5-pro-128k/opengraph-image
Verified Head-to-Head Telemetry