Compare · ModelsLive · 2 picked · head to head
DeepSeek V3.2 vs gpt-oss-20b (free)
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
DeepSeek V3.2 wins on 9/9 benchmarks
DeepSeek V3.2 wins 9 of 9 shared benchmarks. Leads in speed · math · knowledge.
Category leads
speed·DeepSeek V3.2math·DeepSeek V3.2knowledge·DeepSeek V3.2language·DeepSeek V3.2coding·DeepSeek V3.2
Hype vs Reality
Attention vs performance
DeepSeek V3.2
#84 by perf·no signal
gpt-oss-20b (free)
#27 by perf·no signal
Vendor risk
Mixed exposure
One or more vendors flagged
DeepSeek
$3.4B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
9 benchmarks · 2 models
DeepSeek V3.2gpt-oss-20b (free)
Artificial Analysis · Agentic Index
DeepSeek V3.2 leads by +25.3
Artificial Analysis Agentic Index · a composite score measuring how well a model performs in agentic workflows · multi-step tool use, planning, error recovery, and autonomous task completion. Aggregates results from multiple agentic benchmarks including SWE-bench, tool-use tests, and planning evaluations. The canonical single-number metric for "how good is this model as an agent?"
DeepSeek V3.2
52.9
gpt-oss-20b (free)
27.6
Artificial Analysis · Coding Index
DeepSeek V3.2 leads by +18.2
Artificial Analysis Coding Index · a composite score that aggregates performance across multiple coding benchmarks into a single index. Tracks code generation quality, debugging ability, multi-language competence, and real-world software engineering tasks. Used by Artificial Analysis to rank model coding capability in a normalized, comparable format. Useful for developers choosing between models for coding-heavy workloads.
DeepSeek V3.2
36.7
gpt-oss-20b (free)
18.5
Artificial Analysis · Quality Index
DeepSeek V3.2 leads by +17.2
DeepSeek V3.2
41.7
gpt-oss-20b (free)
24.5
OpenCompass · AIME2025
DeepSeek V3.2 leads by +5.1
DeepSeek V3.2
93.0
gpt-oss-20b (free)
87.9
OpenCompass · GPQA-Diamond
DeepSeek V3.2 leads by +15.7
DeepSeek V3.2
84.6
gpt-oss-20b (free)
68.9
OpenCompass · HLE
DeepSeek V3.2 leads by +11.6
DeepSeek V3.2
23.2
gpt-oss-20b (free)
11.6
OpenCompass · IFEval
DeepSeek V3.2 leads by +0.8
DeepSeek V3.2
89.7
gpt-oss-20b (free)
88.9
OpenCompass · LiveCodeBenchV6
DeepSeek V3.2 leads by +7.0
DeepSeek V3.2
75.4
gpt-oss-20b (free)
68.4
OpenCompass · MMLU-Pro
DeepSeek V3.2 leads by +13.0
DeepSeek V3.2
85.8
gpt-oss-20b (free)
72.8
Full benchmark table
| Benchmark | DeepSeek V3.2 | gpt-oss-20b (free) |
|---|---|---|
Artificial Analysis · Agentic Index Artificial Analysis Agentic Index · a composite score measuring how well a model performs in agentic workflows · multi-step tool use, planning, error recovery, and autonomous task completion. Aggregates results from multiple agentic benchmarks including SWE-bench, tool-use tests, and planning evaluations. The canonical single-number metric for "how good is this model as an agent?" | 52.9 | 27.6 |
Artificial Analysis · Coding Index Artificial Analysis Coding Index · a composite score that aggregates performance across multiple coding benchmarks into a single index. Tracks code generation quality, debugging ability, multi-language competence, and real-world software engineering tasks. Used by Artificial Analysis to rank model coding capability in a normalized, comparable format. Useful for developers choosing between models for coding-heavy workloads. | 36.7 | 18.5 |
Artificial Analysis · Quality Index | 41.7 | 24.5 |
OpenCompass · AIME2025 | 93.0 | 87.9 |
OpenCompass · GPQA-Diamond | 84.6 | 68.9 |
OpenCompass · HLE | 23.2 | 11.6 |
OpenCompass · IFEval | 89.7 | 88.9 |
OpenCompass · LiveCodeBenchV6 | 75.4 | 68.4 |
OpenCompass · MMLU-Pro | 85.8 | 72.8 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.25 | $0.38 | 131K tokens (~66 books) | $2.83 | |
| $0.00 | $0.00 | 131K tokens (~66 books) | — |