Coding
Like-for-like- GPT-5.2
- 46.5
- Supported · #83/151
- Mercury 2
- 24.6
- Supported · #149/151
- Basis
- BenchAlign lane · 3 vs 0 public rows
- Reading
- GPT-5.2 leads · intervals overlap
GPT-5.2 vs Mercury 2
Updated September 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. Use the documented cost, context, and runtime rows instead.
0 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Share or export
Which one for your work
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Coding work
Code generation, repair, and software-engineering tasks
GPT-5.2
GPT-5.2 leads on the public coding lane, 46.5 to 24.6, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Long documents
Prompts that approach the documented context limit
GPT-5.2
GPT-5.2 has the larger documented context window.
Confidence: documented
Chat turn cost
1K fresh input + 500 output tokens
Mercury 2
Mercury 2 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
Mercury 2
Mercury 2 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Mercury 2 is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limited
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. Mercury 2 does not fit this workload in one request. GPT-5.2 has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
15 GPT-5.2 only
- Shared results
- 0
- GPT-5.2 only
- 15
- Mercury 2 only
- 0
- Like-for-like categories
- 1 / 8
1 category rests on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.
Agentic
Directional only- GPT-5.2
- 42.9
- Supported · #106/152
- Mercury 2
- 38.1
- Estimated · #124/152
- Basis
- BenchAlign lane · 4 vs 0 public rows
- Reading
- Directional only
Reasoning
Not comparable- GPT-5.2
- 53.7
- Unranked · 3 rankable rows
- Mercury 2
- Not ranked
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Knowledge
Not comparable- GPT-5.2
- 61.8
- Supported · #30/182
- Mercury 2
- Not ranked
- Basis
- BenchAlign lane · 1 vs 0 public rows
- Reading
- Not comparable
Math
Not comparable- GPT-5.2
- 57.5
- Unranked · 2 rankable rows
- Mercury 2
- Not ranked
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- GPT-5.2
- Not ranked
- Mercury 2
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- GPT-5.2
- 66.3
- #23/48
- Mercury 2
- Not ranked
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- GPT-5.2
- 92.6
- #14/121
- Mercury 2
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | GPT-5.2 | Mercury 2 | Basis | Reading |
|---|---|---|---|---|
| Coding | 46.5Supported · #83/151 | 24.6Supported · #149/151 | Like-for-likeBenchAlign lane · 3 vs 0 public rows | GPT-5.2 leads · intervals overlap |
| Agentic | 42.9Supported · #106/152 | 38.1Estimated · #124/152 | Directional onlyBenchAlign lane · 4 vs 0 public rows | Directional only |
| Reasoning | 53.7Unranked · 3 rankable rows | Not ranked | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Knowledge | 61.8Supported · #30/182 | Not ranked | Not comparableBenchAlign lane · 1 vs 0 public rows | Not comparable |
| Math | 57.5Unranked · 2 rankable rows | Not ranked | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | 66.3#23/48 | Not ranked | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
| Instruction following | 92.6#14/121 | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
Shape of the matched evidence
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
A shared-evidence shape is not available.
BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.
What each workload costs
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
Chat turn
1K fresh input + 500 output tokens
- GPT-5.2
- $0.00875
- Fits in one request
- Mercury 2
- $0.00063
- Fits in one request
Mercury 2 has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- GPT-5.2
- $0.1295
- Fits in one request
- Mercury 2
- $0.01475
- Fits in one request
Mercury 2 has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- GPT-5.2
- $0.525
- Fits in one request
- Cached input priced at the published list-input rate
- Mercury 2
- $0.0175
- Does not fit in one request
Mercury 2 does not fit this workload in one request. GPT-5.2 has no published cached-input rate, so cached tokens use its listed input rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationGPT-5.2Mercury 2
Context window
Maximum documented context; output-token limits may be lower.
GPT-5.2
400K
Mercury 2
128K
API model ID
GPT-5.2
Not sourced
Mercury 2
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
GPT-5.2
Not published
Mercury 2
$0.025 per 1M cached input tokens
Documented inputs
GPT-5.2
Not sourced
Mercury 2
Not sourced
Documented outputs
GPT-5.2
Not sourced
Mercury 2
Not sourced
Provider availability
GPT-5.2
Not sourced
Mercury 2
Not sourced
Reasoning profile
GPT-5.2
Reasoning
Mercury 2
Reasoning
Weight access
GPT-5.2
Proprietary
Mercury 2
Proprietary
License
GPT-5.2
Proprietary
Mercury 2
Proprietary
Release date
GPT-5.2
2025-12-11
Mercury 2
2026-02-24
If you already use one of these models
- Deployment change
- The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
- Quality signal
- The public evidence has no benchmark result shared by both models, so it does not support a quality verdict.
- Workload cost
- Repository review: $0.1295 vs $0.01475. Cache-heavy agent loop: $0.525 vs $0.0175.
- Context tradeoff
- GPT-5.2 has the larger documented window (400K).
Run the same representative tasks against both endpoints before changing production traffic.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Frequently asked questions
Which is better, GPT-5.2 or Mercury 2?
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, GPT-5.2 or Mercury 2?
GPT-5.2 leads the public coding lane, 46.5 to 24.6, with Supported evidence for both models, although the 90% intervals overlap.
Which is better for agentic tasks, GPT-5.2 or Mercury 2?
GPT-5.2 scores higher for agentic tasks on the public lane, 42.9 to 38.1. Mercury 2 is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which costs less, GPT-5.2 or Mercury 2?
For the stated presets, chat costs $0.00875 on GPT-5.2 and $0.00063 on Mercury 2; repository review costs $0.1295 and $0.01475; the cache-heavy agent loop costs $0.525 and $0.0175. Mercury 2 does not fit this workload in one request. GPT-5.2 has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, GPT-5.2 or Mercury 2?
GPT-5.2 has the larger documented context window: 400K, compared with 128K.
Related comparisons
Last updated September 10, 2026
Watch GPT-5.2 vs Mercury 2
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.