Skip to main content

Model comparison

DeepSeek-R1 vs Qwen2.5-72B

Data verified

Head-to-head evidence from 0 shared benchmark results across 0 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

No sourced benchmark result is currently shared by both models. This page therefore compares only the available metadata, pricing, and runtime rows; it does not name a quality winner.
DeepSeek
51.67/100
No comparison
N/A
0 category wins0 category wins

Public leaderboard positions: DeepSeek-R1 #103 (Supported); Qwen2.5-72B #101 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. DeepSeek-R1 and Qwen2.5-72B share 0 comparable benchmark results. 0 of 8 categories are comparable. 11 results are unique to DeepSeek-R1; 0 to Qwen2.5-72B.

Updated July 20, 2026
Shared results
0
DeepSeek-R1 only
11
Qwen2.5-72B only
0
Comparable categories
0 / 8

Benchmark data for DeepSeek-R1 and Qwen2.5-72B is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 0 shared benchmark results across 0 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

BenchLM does not have sourced benchmark coverage for Qwen2.5-72B yet. This comparison is currently limited to metadata such as context window, reasoning mode, and pricing where available.

DeepSeek-R1 is priced at $0.55 input / $2.19 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Qwen2.5-72B.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricDeepSeek-R1Qwen2.5-72BComparison
Input / output priceUSD per 1M tokensDeepSeek-R1$0.55 input / $2.19 outputQwen2.5-72B$0 input / $0 outputQwen2.5-72B has the lower combined listed price.
Generation speedtokens per secondDeepSeek-R1Not availableQwen2.5-72BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenDeepSeek-R1Not availableQwen2.5-72BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensDeepSeek-R1128KQwen2.5-72B128KListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkDeepSeek-R1Qwen2.5-72BResult
τ²-bench resultsSource 36.5%Not comparable
Coding
BenchmarkDeepSeek-R1Qwen2.5-72BResult
AA-SciCodeSource 40.3%Not comparable
Reasoning
BenchmarkDeepSeek-R1Qwen2.5-72BResult
AA-LCRSource 54.7%Not comparable
CritPtSource 1.4%Not comparable
Knowledge
BenchmarkDeepSeek-R1Qwen2.5-72BResult
Artificial Analysis Intelligence IndexSource 20.1%Not comparable
AA-GPQA DiamondSource 81.3%Not comparable
AA-HLESource 14.9%Not comparable
AA-Omniscience IndexSource -27.1%Not comparable
AA-Omniscience AccuracySource 31.0%Not comparable
AA-Omniscience Hallucination RateSource 84.0%Not comparable
Inst. Following
BenchmarkDeepSeek-R1Qwen2.5-72BResult
AA-IFBenchSource 39.6%Not comparable
Frequently Asked Questions (3)

Can I compare DeepSeek-R1 and Qwen2.5-72B on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.

Why does this comparison show “coming soon”?

BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.

What data is available for DeepSeek-R1 and Qwen2.5-72B today?

DeepSeek-R1: $0.55 input / $2.19 output per 1M tokens Qwen2.5-72B: $0.00 input / $0.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

DeepSeek-R1
API / mo$2,055
Self-host / mo$18,221
Break-even583M/day
Qwen2.5-72B
API / mo$0
Self-host / moNot listed
Break-even
Proprietary model — self-hosting not applicable.
Model the full break-even

Related Comparisons

Last updated: July 20, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.