Updated October 23, 2026. Rank says GPT-5.6 Terra is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
GPT-5.6 Terra has the higher public point estimate, 70.04 versus 33.38. Their conditional score ranges do not overlap. These ranges do not establish rank confidence. 2 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
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.
Tool use, computer use, and multi-step task completion
GPT-5.6 Terra
GPT-5.6 Terra has the higher public agentic point estimate, 60.4 to 12, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Prompts that approach the documented context limit
GPT-5.6 Terra
GPT-5.6 Terra has the larger documented context window.
1K fresh input + 500 output tokens
Mercury 2.5
Mercury 2.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
Mercury 2.5
Mercury 2.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
50K fresh input + 3K output tokens
Mercury 2.5
Mercury 2.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Mercury 2.5 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.
The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.
Directional only · BenchAlign v5.8
GPT-5.6 Terra has the higher coding point estimate. Conditional score ranges do not establish rank confidence.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
2 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
Each row shows the public-lane category score for both models: the BenchAlign v5.8 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.
| Category | GPT-5.6 Terra | Mercury 2.5 | Basis | Reading |
|---|---|---|---|---|
| Agentic | 60.4Supported · #27/132 | 12.0Supported · #123/132 | Like-for-likeBenchAlign v5.8 lane · 10 vs 3 public rows | GPT-5.6 Terra leads |
| Knowledge | 69.6Supported · #18/187 | 33.8Supported · #139/187 | Like-for-likeBenchAlign v5.8 lane · 8 vs 1 public rows | GPT-5.6 Terra leads |
| Coding | 61.9Supported · #15/153 | 16.1Estimated · #133/153 | Directional onlyBenchAlign v5.8 lane · 9 vs 1 public rows | Directional only |
| Instruction following | 87.1#41/153 | 81.1#60/153 | Directional onlyProvisional lane · 0 vs 1 weighted rows | Directional only |
| Reasoning | 69.1#19/27 | 71.7Unranked · 2 rankable rows | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
| Multimodal | 84.9#12/56 | Not ranked | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 90.1Unranked · 3 rankable rows | Not ranked | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
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.
1K fresh input + 500 output tokens
Mercury 2.5 has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
Mercury 2.5 has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
Mercury 2.5 has the lower modeled cost
Costs use the listed standard API rates.
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
Maximum documented context; output-token limits may be lower.
GPT-5.6 Terra
1.05M
OpenAI model catalogMercury 2.5
GPT-5.6 Terra
gpt-5.6-terra
OpenAI model catalogMercury 2.5
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
GPT-5.6 Terra
$0.2 per 1M cached input tokens
OpenAI pricingMercury 2.5
$0.004 per 1M cached input tokens
Inception models and Mercury 2.5 launch pricingGPT-5.6 Terra
text, image
OpenAI model catalogMercury 2.5
Not sourced
GPT-5.6 Terra
Mercury 2.5
Not sourced
GPT-5.6 Terra
Generally Available · OpenAI Responses API
OpenAI model catalogMercury 2.5
Not sourced
GPT-5.6 Terra
Reasoning
Mercury 2.5
Reasoning
GPT-5.6 Terra
Proprietary
Mercury 2.5
Proprietary
GPT-5.6 Terra
Proprietary
Mercury 2.5
Proprietary
GPT-5.6 Terra
2026-07-09
Mercury 2.5
2026-09-08
GPT-5.6 Terra has the higher public point estimate, 70.04 versus 33.38. Their conditional score ranges do not overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.
GPT-5.6 Terra scores higher for coding on the public lane, 61.9 to 16.1. Mercury 2.5 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
GPT-5.6 Terra has the higher public agentic tasks point estimate, 60.4 to 12, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
For the stated presets, chat costs $0.008 on GPT-5.6 Terra and $0.00012 on Mercury 2.5; repository review costs $0.136 and $0.00245; the cache-heavy agent loop costs $0.2 and $0.0031. Costs use the listed standard API rates.
GPT-5.6 Terra has the larger documented context window: 1.05M, compared with 260K.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Terminal-Bench 3.0
Not directly comparable
Terminal-Bench 2.1
Not directly comparable
BrowseComp
Not directly comparable
OSWorld 2.0
Not directly comparable
CyberGym
Not directly comparable
ExploitGym
Not directly comparable
Toolathlon
Not directly comparable
Terminal-Bench 2.1 (Vals)
GPT-5.6 Terra leads this result
ApprenticeBench
Not directly comparable
MazeBench
Not directly comparable
τ³-bench results
Not directly comparable
DeepSearchQA
Not directly comparable
SWE-bench Pro
Not directly comparable
Terminal-Bench 2.1
Not directly comparable
DeepSWE
Not directly comparable
FrontierCode 1.1 Extended
Not directly comparable
CursorBench 3.2
Not directly comparable
VulcanBench v3
Not directly comparable
LiveCodeBench (Vals)
Not directly comparable
SWE-bench (Vals)
Not directly comparable
CursorBench 4.0
Not directly comparable
SciCode
Not directly comparable
ExtractBench (LlamaIndex)
Not directly comparable
ParseBench
Not directly comparable
MMMU-Pro
Not directly comparable
MMMU-Pro w/ Python
Not directly comparable
GPQA
Not directly comparable
GPQA-D
GPT-5.6 Terra leads this result
HLE-Verified
Not directly comparable
LABBench2
Not directly comparable
HealthBench Professional
Not directly comparable
HealthBench Hard
Not directly comparable
GPQA Diamond (Vals)
Not directly comparable
MMLU-Pro (Vals)
Not directly comparable
IFBench
Not directly comparable
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 5,600+ readers.
Last updated October 23, 2026
