| Signal | gpt-oss-20b | Delta | Mercury |
|---|---|---|---|
Capabilities | 67 | +17 | |
Benchmarks | 56 | +2 | |
Pricing | 100 | +1 | |
Context window size | 81 | +0 | |
Recency | 89 | +7 | |
Output Capacity | 85 | +10 | |
| Overall Result | 6 wins | of 6 | 0 wins |
Score History
57.6
current score
gpt-oss-20b
right now
55.3
current score
OpenAI
Inception
gpt-oss-20b saves you $54.00/month
That's $648.00/year compared to Mercury at your current usage level of 100K calls/month.
| Metric | gpt-oss-20b | Mercury | Winner |
|---|---|---|---|
| Overall Score | 58 | 55 | gpt-oss-20b |
| Rank | #103 | #105 | gpt-oss-20b |
| Quality Rank | #103 | #105 | gpt-oss-20b |
| Adoption Rank | #103 | #105 | gpt-oss-20b |
| Parameters | 20B | -- | -- |
| Context Window | 131K | 128K | gpt-oss-20b |
| Pricing | $0.03/$0.11/M | $0.25/$0.75/M | -- |
| Signal Scores | |||
| Capabilities | 67 | 50 | gpt-oss-20b |
| Benchmarks | 56 | 54 | gpt-oss-20b |
| Pricing | 100 | 99 | gpt-oss-20b |
| Context window size | 81 | 81 | gpt-oss-20b |
| Recency | 89 | 82 | gpt-oss-20b |
| Output Capacity | 85 | 75 | gpt-oss-20b |
Our score (0-100) is driven by benchmark performance (90%) from Arena Elo ratings, MMLU, GPQA, HumanEval, SWE-bench, and 15+ standardized evaluations. Capabilities and context window serve as tiebreakers (10%). Learn more about our methodology.
Scores 58/100 (rank #103), placing it in the top 65% of all 290 models tracked.
Scores 55/100 (rank #105), placing it in the top 64% of all 290 models tracked.
With only a 2-point gap, these models are in the same performance tier. The practical difference in output quality is minimal - your choice should depend on pricing, latency requirements, and specific feature needs.
gpt-oss-20b offers 86% better value per quality point. At 1M tokens/day, you'd spend $2.10/month with gpt-oss-20b vs $15.00/month with Mercury - a $12.90 monthly difference.
Both models have comparable response speeds. For most applications, the latency difference is negligible.
When latency matters most: Interactive chatbots, IDE code completion, real-time translation, and user-facing applications where response time directly impacts experience. For batch processing, background summarization, or offline analysis, latency is less critical.
Code generation & review
Higher benchmark score (0/100) indicates stronger performance on coding tasks like generating functions, debugging, and refactoring
Customer support chatbot
Faster response time (speed score 0/100) is critical for user-facing chat. gpt-oss-20b also offers lower per-token costs for high-volume support
Long document analysis
Larger context window (131K tokens) can process longer documents, contracts, and research papers in a single pass
Batch data extraction
Lower output pricing ($0.11/M) reduces costs when processing thousands of records daily
Creative writing & content
Higher overall composite score (58/100) correlates with better nuance, coherence, and style in long-form content
gpt-oss-20b and Mercury are extremely close in overall performance (only 2.3000000000000043 points apart). Your best choice depends entirely on which specific strengths matter most for your use case.
Best for Quality
gpt-oss-20b
Marginally better benchmark scores; both are excellent
Best for Cost
gpt-oss-20b
86% lower pricing; better value at scale
Best for Reliability
gpt-oss-20b
Higher uptime and faster response speeds
Best for Prototyping
gpt-oss-20b
Stronger community support and better developer experience
Best for Production
gpt-oss-20b
Wider enterprise adoption and proven at scale
by OpenAI
| Capability | gpt-oss-20b | Mercury |
|---|---|---|
| Vision (Image Input) | ||
| Function Calling | ||
| Streaming | ||
| JSON Mode | ||
| Reasoningdiffers | ||
| Web Search | ||
| Image Output |
OpenAI
Inception
gpt-oss-20b saves you $1.16/month
That's 86% cheaper than Mercury at 1,000 tokens/request and 100 requests/day.
Assumes 60% input / 40% output token ratio per request. Actual costs may vary based on your usage pattern.
| Parameter | gpt-oss-20b | Mercury |
|---|---|---|
| Context Window | 131K | 128K |
| Max Output Tokens | 131,072 | 32,000 |
| Open Source | Yes | No |
| Created | Aug 5, 2025 | Jun 26, 2025 |
gpt-oss-20b scores 58/100 (rank #103) compared to Mercury's 55/100 (rank #105), giving it a 2-point advantage. gpt-oss-20b is the stronger overall choice, though Mercury may excel in specific areas like certain benchmarks.
gpt-oss-20b is ranked #103 and Mercury is ranked #105 out of 290+ AI models. Rankings use a composite score combining benchmark performance (90%) from MMLU, GPQA, HumanEval, SWE-bench, and 15+ standardized evaluations, with capabilities and context window as tiebreakers (10%). Scores update hourly.
gpt-oss-20b is cheaper at $0.11/M output tokens vs Mercury's $0.75/M output tokens - 6.8x more expensive. Input token pricing: gpt-oss-20b at $0.03/M vs Mercury at $0.25/M.
gpt-oss-20b has a larger context window of 131,072 tokens compared to Mercury's 128,000 tokens. A larger context window means the model can process longer documents and conversations.