Math
Like-for-like- GPT-5.5 Pro
- 48.1
- GPT-5.6 Terra
- 80.8
- Weighted basis
- 2 vs 2 rows
- Reading
- GPT-5.6 Terra leads
Model comparison
GPT-5.5 Pro vs GPT-5.6 Terra
Updated August 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
GPT-5.6 Terra has the higher public score estimate, 72.29 versus 62.95, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
4 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.
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.
Chat turn cost
1K fresh input + 500 output tokens
GPT-5.6 Terra
GPT-5.6 Terra has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
GPT-5.6 Terra
GPT-5.6 Terra has the lower estimated token cost for this stated workload. GPT-5.5 Pro has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
GPT-5.6 Terra
GPT-5.6 Terra has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
No shared weighted benchmark basis supports a winner.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.
Confidence: limited
Long documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
2 GPT-5.5 Pro only
4 Shared
18 GPT-5.6 Terra only
- Shared results
- 4
- GPT-5.5 Pro only
- 2
- GPT-5.6 Terra only
- 18
- Like-for-like categories
- 1 / 8
1 category uses different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.
Agentic
Directional only- GPT-5.5 Pro
- 90.1
- GPT-5.6 Terra
- 87.4
- Weighted basis
- 1 vs 2 rows
- Reading
- Directional only
Coding
Not comparable- GPT-5.5 Pro
- Not measured
- GPT-5.6 Terra
- 63.4
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Reasoning
Not comparable- GPT-5.5 Pro
- Not measured
- GPT-5.6 Terra
- 83.9
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Knowledge
Not comparable- GPT-5.5 Pro
- 57.2
- GPT-5.6 Terra
- 92.9
- Weighted basis
- 1 vs 1 rows
- Reading
- Not comparable
Multilingual
Not comparable- GPT-5.5 Pro
- Not measured
- GPT-5.6 Terra
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- GPT-5.5 Pro
- Not measured
- GPT-5.6 Terra
- 80.7
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Instruction following
Not comparable- GPT-5.5 Pro
- Not measured
- GPT-5.6 Terra
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | GPT-5.5 Pro | GPT-5.6 Terra | Weighted basis | Reading |
|---|---|---|---|---|
| Math | 48.1 | 80.8 | Like-for-like2 vs 2 rows | GPT-5.6 Terra leads |
| Agentic | 90.1 | 87.4 | Directional only1 vs 2 rows | Directional only |
| Coding | Not measured | 63.4 | Not comparable0 vs 1 rows | Not comparable |
| Reasoning | Not measured | 83.9 | Not comparable0 vs 1 rows | Not comparable |
| Knowledge | 57.2 | 92.9 | Not comparable1 vs 1 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multimodal | Not measured | 80.7 | Not comparable0 vs 1 rows | Not comparable |
| Instruction following | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
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.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
FrontierMath v2 (Tiers 1-3)
Math
GPT-5.5 Pro: 51.000%GPT-5.6 Terra: 84.900%Normalized gap 33.9GPT-5.5 Pro source GPT-5.6 Terra sourceFrontierMath v2 (Tier 4)
Math
GPT-5.5 Pro: 39.600%GPT-5.6 Terra: 68.300%Normalized gap 28.7GPT-5.5 Pro source GPT-5.6 Terra sourceBrowseComp
Agentic
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-5.5 Pro
- $0.12
- Fits in one request
- GPT-5.6 Terra
- $0.008
- Fits in one request
GPT-5.6 Terra has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- GPT-5.5 Pro
- $2.04
- Fits in one request
- GPT-5.6 Terra
- $0.136
- Fits in one request
GPT-5.6 Terra 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-5.5 Pro
- $8.40
- Fits in one request
- Cached input priced at the published list-input rate
- GPT-5.6 Terra
- $0.2
- Fits in one request
GPT-5.6 Terra has the lower modeled cost
GPT-5.5 Pro 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-5.5 ProGPT-5.6 Terra
Context window
Maximum documented context; output-token limits may be lower.
GPT-5.5 Pro
GPT-5.6 Terra
1.05M
OpenAI model catalogAPI model ID
GPT-5.5 Pro
gpt-5.5-pro
OpenAI GPT-5.5 Pro model documentationGPT-5.6 Terra
gpt-5.6-terra
OpenAI model catalogCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
GPT-5.5 Pro
Not published
OpenAI pricingGPT-5.6 Terra
$0.2 per 1M cached input tokens
OpenAI pricingDocumented inputs
GPT-5.5 Pro
text, image
OpenAI model catalogGPT-5.6 Terra
text, image
OpenAI model catalogDocumented outputs
GPT-5.5 Pro
GPT-5.6 Terra
Provider availability
GPT-5.5 Pro
Generally Available · OpenAI Responses API
OpenAI model catalogGPT-5.6 Terra
Generally Available · OpenAI Responses API
OpenAI model catalogReasoning profile
GPT-5.5 Pro
Reasoning
GPT-5.6 Terra
Reasoning
Weight access
GPT-5.5 Pro
Proprietary
GPT-5.6 Terra
Proprietary
License
GPT-5.5 Pro
Proprietary
GPT-5.6 Terra
Proprietary
Release date
GPT-5.5 Pro
2026-04-23
GPT-5.6 Terra
2026-07-09
If you already use one of these models
- Deployment change
- Both entries list OpenAI as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
- Quality signal
- GPT-5.6 Terra has the higher public score estimate, 72.29 versus 62.95, but the 90% score intervals overlap.
- Workload cost
- Repository review: $2.04 vs $0.136. Cache-heavy agent loop: $8.40 vs $0.2.
- Context tradeoff
- Both models list 1.05M.
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.
Browse raw public benchmark evidence24 rows
Agentic
BrowseComp
GPT-5.5 Pro90.1%SourceGPT-5.6 Terra87.5%SourceGPT-5.5 Pro leads this result
Terminal-Bench 2.0
GPT-5.5 Pro—GPT-5.6 Terra87.4%SourceNot directly comparable
OSWorld 2.0
GPT-5.5 Pro—GPT-5.6 Terra50.2%SourceNot directly comparable
CyberGym
GPT-5.5 Pro—GPT-5.6 Terra81.8%SourceNot directly comparable
ExploitGym
GPT-5.5 Pro—GPT-5.6 Terra23.2%SourceNot directly comparable
Toolathlon
GPT-5.5 Pro—GPT-5.6 Terra53.1%SourceNot directly comparable
Coding
SWE-bench Pro
GPT-5.5 Pro—GPT-5.6 Terra63.4%SourceNot directly comparable
Terminal-Bench 2.0
GPT-5.5 Pro—GPT-5.6 Terra87.4%SourceNot directly comparable
deepSwe
GPT-5.5 Pro—GPT-5.6 Terra69.6%SourceNot directly comparable
FrontierCode 1.1 Extended
GPT-5.5 Pro—GPT-5.6 Terra55.8%SourceNot directly comparable
cursorBench32
GPT-5.5 Pro—GPT-5.6 Terra64.9%SourceNot directly comparable
Reasoning
Knowledge
HLE
GPT-5.5 Pro57.2%SourceGPT-5.6 Terra—Not directly comparable
HLE w/o tools
GPT-5.5 Pro43.1%SourceGPT-5.6 Terra—Not directly comparable
GPQA
GPT-5.5 Pro—GPT-5.6 Terra92.9%SourceNot directly comparable
GPQA-D
GPT-5.5 Pro—GPT-5.6 Terra92.9%SourceNot directly comparable
HealthBench Professional
GPT-5.5 Pro—GPT-5.6 Terra57.7%SourceNot directly comparable
HealthBench Hard
GPT-5.5 Pro—GPT-5.6 Terra32.7%SourceNot directly comparable
Math
FrontierMath (legacy)
GPT-5.5 Pro52.4%SourceGPT-5.6 Terra84.9%SourceGPT-5.6 Terra leads this result
FrontierMath v2 (Tiers 1-3)
GPT-5.5 Pro51.000%SourceGPT-5.6 Terra84.900%SourceGPT-5.6 Terra leads this result
FrontierMath v2 (Tier 4)
GPT-5.5 Pro39.600%SourceGPT-5.6 Terra68.300%SourceGPT-5.6 Terra leads this result
Multimodal
Frequently asked questions
Which is better, GPT-5.5 Pro or GPT-5.6 Terra?
GPT-5.6 Terra has the higher public score estimate, 72.29 versus 62.95, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, GPT-5.5 Pro or GPT-5.6 Terra?
The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.
Which is better for agentic tasks, GPT-5.5 Pro or GPT-5.6 Terra?
The current agentic tasks averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.
Which costs less, GPT-5.5 Pro or GPT-5.6 Terra?
For the stated presets, chat costs $0.12 on GPT-5.5 Pro and $0.008 on GPT-5.6 Terra; repository review costs $2.04 and $0.136; the cache-heavy agent loop costs $8.40 and $0.2. GPT-5.5 Pro has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, GPT-5.5 Pro or GPT-5.6 Terra?
Both models list the same context window, 1.05M.
Related comparisons
Last updated August 10, 2026
Watch GPT-5.5 Pro vs GPT-5.6 Terra
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.