Compare · ModelsLive · 2 picked · head to head
gpt-oss-20b vs Claude 3.5 Sonnet
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude 3.5 Sonnet wins on 4/6 benchmarks
Claude 3.5 Sonnet wins 4 of 6 shared benchmarks. Leads in arena · language · reasoning.
Category leads
arena·Claude 3.5 Sonnetknowledge·gpt-oss-20blanguage·Claude 3.5 Sonnetmath·gpt-oss-20breasoning·Claude 3.5 Sonnet
Hype vs Reality
Attention vs performance
gpt-oss-20b
#24 by perf·no signal
Claude 3.5 Sonnet
#129 by perf·no signal
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
Anthropic
$380.0B·Tier 1
Head to head
6 benchmarks · 2 models
gpt-oss-20bClaude 3.5 Sonnet
Chatbot Arena Elo · Overall
Claude 3.5 Sonnet leads by +53.7
gpt-oss-20b
1317.7
Claude 3.5 Sonnet
1371.4
HELM · GPQA
gpt-oss-20b leads by +2.9
gpt-oss-20b
59.4
Claude 3.5 Sonnet
56.5
HELM · IFEval
Claude 3.5 Sonnet leads by +12.4
gpt-oss-20b
73.2
Claude 3.5 Sonnet
85.6
HELM · MMLU-Pro
Claude 3.5 Sonnet leads by +3.7
gpt-oss-20b
74.0
Claude 3.5 Sonnet
77.7
HELM · Omni-MATH
gpt-oss-20b leads by +28.9
gpt-oss-20b
56.5
Claude 3.5 Sonnet
27.6
HELM · WildBench
Claude 3.5 Sonnet leads by +5.5
gpt-oss-20b
73.7
Claude 3.5 Sonnet
79.2
Full benchmark table
| Benchmark | gpt-oss-20b | Claude 3.5 Sonnet |
|---|---|---|
Chatbot Arena Elo · Overall | 1317.7 | 1371.4 |
HELM · GPQA | 59.4 | 56.5 |
HELM · IFEval | 73.2 | 85.6 |
HELM · MMLU-Pro | 74.0 | 77.7 |
HELM · Omni-MATH | 56.5 | 27.6 |
HELM · WildBench | 73.7 | 79.2 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.03 | $0.14 | 131K tokens (~66 books) | $0.57 | |
| — | — | — | — |