Compare · ModelsLive · 2 picked · head to head
DeepSeek V4 Flash vs gpt-oss-120b
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
DeepSeek V4 Flash wins on 13/14 benchmarks
DeepSeek V4 Flash wins 13 of 14 shared benchmarks. Leads in speed · arena · general.
Category leads
speed·DeepSeek V4 Flasharena·DeepSeek V4 Flashgeneral·DeepSeek V4 Flashcoding·DeepSeek V4 Flashreasoning·DeepSeek V4 Flashlanguage·DeepSeek V4 Flashmath·DeepSeek V4 Flashknowledge·DeepSeek V4 Flash
Hype vs Reality
Attention vs performance
DeepSeek V4 Flash
#39 by perf·#6 by attention
gpt-oss-120b
#127 by perf·no signal
Best value
gpt-oss-120b
5.0x better value than DeepSeek V4 Flash
DeepSeek V4 Flash
94.4 pts/$
$0.65/M
gpt-oss-120b
475.4 pts/$
$0.10/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 V4 Flashgpt-oss-120b
Artificial Analysis · Quality Index
DeepSeek V4 Flash leads by +28.7
DeepSeek V4 Flash
40.3
gpt-oss-120b
11.6
Chatbot Arena Elo · Overall
DeepSeek V4 Flash leads by +84.4
DeepSeek V4 Flash
1436.0
gpt-oss-120b
1351.6
Dtbench
DeepSeek V4 Flash leads by +16.9
DeepSeek V4 Flash
77.3
gpt-oss-120b
60.5
LiveBench · Agentic Coding
DeepSeek V4 Flash leads by +33.3
DeepSeek V4 Flash
50.0
gpt-oss-120b
16.7
LiveBench · Coding
DeepSeek V4 Flash leads by +9.0
DeepSeek V4 Flash
69.2
gpt-oss-120b
60.2
LiveBench · Data Analysis
DeepSeek V4 Flash leads by +29.2
DeepSeek V4 Flash
68.0
gpt-oss-120b
38.8
LiveBench · If
DeepSeek V4 Flash leads by +12.9
DeepSeek V4 Flash
63.1
gpt-oss-120b
50.3
LiveBench · Language
DeepSeek V4 Flash leads by +21.5
DeepSeek V4 Flash
70.1
gpt-oss-120b
48.6
LiveBench · Mathematics
DeepSeek V4 Flash leads by +10.8
DeepSeek V4 Flash
79.7
gpt-oss-120b
68.9
LiveBench · Overall
DeepSeek V4 Flash leads by +21.2
DeepSeek V4 Flash
67.3
gpt-oss-120b
46.1
LiveBench · Reasoning
DeepSeek V4 Flash leads by +31.4
DeepSeek V4 Flash
70.6
gpt-oss-120b
39.2
Lmca
DeepSeek V4 Flash leads by +16.2
DeepSeek V4 Flash
42.2
gpt-oss-120b
26.1
SimpleBench
DeepSeek V4 Flash leads by +29.0
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
DeepSeek V4 Flash
35.6
gpt-oss-120b
6.5
WeirdML
gpt-oss-120b leads by +2.5
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
DeepSeek V4 Flash
45.6
gpt-oss-120b
48.2
Full benchmark table
| Benchmark | DeepSeek V4 Flash | gpt-oss-120b |
|---|---|---|
Artificial Analysis · Quality Index | 40.3 | 11.6 |
Chatbot Arena Elo · Overall | 1436.0 | 1351.6 |
Dtbench | 77.3 | 60.5 |
LiveBench · Agentic Coding | 50.0 | 16.7 |
LiveBench · Coding | 69.2 | 60.2 |
LiveBench · Data Analysis | 68.0 | 38.8 |
LiveBench · If | 63.1 | 50.3 |
LiveBench · Language | 70.1 | 48.6 |
LiveBench · Mathematics | 79.7 | 68.9 |
LiveBench · Overall | 67.3 | 46.1 |
LiveBench · Reasoning | 70.6 | 39.2 |
Lmca | 42.2 | 26.1 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 35.6 | 6.5 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 45.6 | 48.2 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.03 | $1.28 | 1.0M tokens (~524 books) | $3.39 | |
| $0.04 | $0.17 | 131K tokens (~66 books) | $0.70 |
People also compared
DeepSeek V3.2 Speciale vs DeepSeek V4 FlashDeepSeek-V2 (MoE-236B, May 2024) vs DeepSeek V4 FlashDeepSeek V4 Flash vs PaLM 2-MDeepSeek V4 Flash vs Qwen3 Next 80B A3B ThinkingDeepSeek V4 Flash vs Qwen3.7 MaxDeepSeek V4 Flash vs o3 ProDeepSeek V4 Flash vs Qwen-14BDeepSeek V4.1 Flash vs DeepSeek V4 Flash