Compare · ModelsLive · 2 picked · head to head
DeepSeek V3.2 vs gpt-oss-20b
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
DeepSeek V3.2 wins on 14/14 benchmarks
DeepSeek V3.2 wins 14 of 14 shared benchmarks. Leads in speed · arena · knowledge.
Category leads
speed·DeepSeek V3.2arena·DeepSeek V3.2knowledge·DeepSeek V3.2general·DeepSeek V3.2math·DeepSeek V3.2language·DeepSeek V3.2coding·DeepSeek V3.2
Hype vs Reality
Attention vs performance
DeepSeek V3.2
#142 by perf·no signal
gpt-oss-20b
#97 by perf·no signal
Best value
gpt-oss-20b
7.2x better value than DeepSeek V3.2
DeepSeek V3.2
136.3 pts/$
$0.35/M
gpt-oss-20b
983.3 pts/$
$0.05/M
Vendor risk
Mixed exposure
One or more vendors flagged
DeepSeek
$3.4B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
14 benchmarks · 2 models
DeepSeek V3.2gpt-oss-20b
Artificial Analysis · Quality Index
DeepSeek V3.2 leads by +32.7
DeepSeek V3.2
41.7
gpt-oss-20b
9.0
Chatbot Arena Elo · Overall
DeepSeek V3.2 leads by +107.2
DeepSeek V3.2
1424.8
gpt-oss-20b
1317.6
Chess Puzzles
DeepSeek V3.2 leads by +9.5
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
DeepSeek V3.2
9.5
gpt-oss-20b
0.0
Dtbench
DeepSeek V3.2 leads by +29.3
DeepSeek V3.2
76.0
gpt-oss-20b
46.7
GPQA diamond
DeepSeek V3.2 leads by +30.2
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
DeepSeek V3.2
77.9
gpt-oss-20b
47.7
Lmca
DeepSeek V3.2 leads by +16.8
DeepSeek V3.2
33.9
gpt-oss-20b
17.1
OpenCompass · AIME2025
DeepSeek V3.2 leads by +5.1
DeepSeek V3.2
93.0
gpt-oss-20b
87.9
OpenCompass · GPQA-Diamond
DeepSeek V3.2 leads by +15.7
DeepSeek V3.2
84.6
gpt-oss-20b
68.9
OpenCompass · HLE
DeepSeek V3.2 leads by +11.6
DeepSeek V3.2
23.2
gpt-oss-20b
11.6
OpenCompass · IFEval
DeepSeek V3.2 leads by +0.8
DeepSeek V3.2
89.7
gpt-oss-20b
88.9
OpenCompass · LiveCodeBenchV6
DeepSeek V3.2 leads by +7.0
DeepSeek V3.2
75.4
gpt-oss-20b
68.4
OpenCompass · MMLU-Pro
DeepSeek V3.2 leads by +13.0
DeepSeek V3.2
85.8
gpt-oss-20b
72.8
OTIS Mock AIME 2024-2025
DeepSeek V3.2 leads by +22.6
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
DeepSeek V3.2
87.8
gpt-oss-20b
65.2
Terminal Bench
DeepSeek V3.2 leads by +36.1
Terminal-Bench 2.0 · evaluates AI agents on real terminal-based coding tasks · writing scripts, debugging, running tests, and managing projects entirely through command-line interaction. Tests both code quality and terminal fluency. Claude Opus 4.7 scores 69.4%, demonstrating significant agentic terminal competence.
DeepSeek V3.2
39.5
gpt-oss-20b
3.4
Full benchmark table
| Benchmark | DeepSeek V3.2 | gpt-oss-20b |
|---|---|---|
Artificial Analysis · Quality Index | 41.7 | 9.0 |
Chatbot Arena Elo · Overall | 1424.8 | 1317.6 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 9.5 | 0.0 |
Dtbench | 76.0 | 46.7 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 77.9 | 47.7 |
Lmca | 33.9 | 17.1 |
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 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 87.8 | 65.2 |
Terminal Bench Terminal-Bench 2.0 · evaluates AI agents on real terminal-based coding tasks · writing scripts, debugging, running tests, and managing projects entirely through command-line interaction. Tests both code quality and terminal fluency. Claude Opus 4.7 scores 69.4%, demonstrating significant agentic terminal competence. | 39.5 | 3.4 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.28 | $0.42 | 164K tokens (~82 books) | $3.15 | |
| $0.02 | $0.09 | 131K tokens (~66 books) | $0.36 |