Long documents
Prompts that approach the documented context limit
Gemini 3 Pro
Gemini 3 Pro has the larger documented context window.
Confidence: documented
Gemini 3 Pro vs Hy4 preview
Updated October 13, 2026. Rank cannot separate these two. Price, access, and your workload decide. Public scores include evidence status and uncertainty.
Both of these models will change. Get the price, version and retirement notices for the pair, each with its source. Follow model changes
Share or export
Decision reading
Hy4 preview has the higher public point estimate, 60.86 versus 60.62. Their conditional score ranges overlap. These ranges do not establish rank confidence. 1 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
- Shared results
- 1
- Gemini 3 Pro only
- 26
- Hy4 preview only
- 29
- Like-for-like categories
- 0 / 8
Supported: Gemini 3 Pro · Estimated: Hy4 preview. Conditional ranges do not establish rank confidence.How the comparison works
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.
Show secondary and unsupported calls
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Gemini 3 Pro is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limitedAgentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Gemini 3 Pro is not ranked on the public lane for agentic, so no winner is named for agentic.
Confidence: limitedChat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-ratesCache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: rate-fallbackRepository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Which one for a specific job
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.
43.2Gemini 3 Pro57.1Hy4 preview
Directional only · BenchAlign v5.8
Hy4 preview 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.
Same basis rules as the category table below
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
26 Gemini 3 Pro only
1 Shared
29 Hy4 preview only
2 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
Category results, on a stated basis
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.
Coding
Directional only- Gemini 3 Pro
- 43.2
- Estimated · #58/148
- Hy4 preview
- 57.1
- Supported · #26/148
- Basis
- BenchAlign v5.8 lane · 1 vs 8 public rows
- Reading
- Directional only
Knowledge
Directional only- Gemini 3 Pro
- 60.2
- Estimated · #46/180
- Hy4 preview
- 63.6
- Estimated · #39/180
- Basis
- BenchAlign v5.8 lane · 0 vs 4 public rows
- Reading
- Directional only
Agentic
Not comparable- Gemini 3 Pro
- Not ranked
- Hy4 preview
- 54.5
- Estimated · #37/123
- Basis
- BenchAlign v5.8 lane · 2 vs 15 public rows
- Reading
- Not comparable
Reasoning
Not comparable- Gemini 3 Pro
- 50.1
- Unranked · 4 rankable rows
- Hy4 preview
- Not ranked
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Gemini 3 Pro
- 80.0
- #18/54
- Hy4 preview
- 88.3
- Unranked · 1 rankable row
- Basis
- Provisional lane · 2 vs 1 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Gemini 3 Pro
- Not ranked
- Hy4 preview
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Gemini 3 Pro
- 86.1
- #43/127
- Hy4 preview
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Gemini 3 Pro
- Not ranked
- Hy4 preview
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Gemini 3 Pro | Hy4 preview | Basis | Reading |
|---|---|---|---|---|
| Coding | 43.2Estimated · #58/148 | 57.1Supported · #26/148 | Directional onlyBenchAlign v5.8 lane · 1 vs 8 public rows | Directional only |
| Knowledge | 60.2Estimated · #46/180 | 63.6Estimated · #39/180 | Directional onlyBenchAlign v5.8 lane · 0 vs 4 public rows | Directional only |
| Agentic | Not ranked | 54.5Estimated · #37/123 | Not comparableBenchAlign v5.8 lane · 2 vs 15 public rows | Not comparable |
| Reasoning | 50.1Unranked · 4 rankable rows | Not ranked | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Multimodal | 80.0#18/54 | 88.3Unranked · 1 rankable row | Not comparableProvisional lane · 2 vs 1 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | 86.1#43/127 | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | Not ranked | 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 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.
Supported evidence per lane · bars run 0–100Methodology
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
- Gemini 3 Pro
- $0.008
- Fits in one request
- Hy4 preview
- Self-hosted; infrastructure cost varies
- Fits in one request
Hy4 preview has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Gemini 3 Pro
- $0.136
- Fits in one request
- Hy4 preview
- Self-hosted; infrastructure cost varies
- Fits in one request
Hy4 preview has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Gemini 3 Pro
- $0.56
- Fits in one request
- Cached input priced at the published list-input rate
- Hy4 preview
- Self-hosted; infrastructure cost varies
- Fits in one request
- Cached-input rate unavailable
Gemini 3 Pro has no published cached-input rate, so cached tokens use its listed input rate. Hy4 preview has no comparable published API token rate.
Cached input falls back to the list input rate only where a cached rate is unpublished
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationGemini 3 ProHy4 preview
Context window
Maximum documented context; output-token limits may be lower.
Gemini 3 Pro
2M
Hy4 preview
API model ID
Gemini 3 Pro
Not sourced
Hy4 preview
tencent/Hy4-preview
Tencent Hy4 preview model cardCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Gemini 3 Pro
Not published
Hy4 preview
No comparable hosted API rate
Tencent Hy4 preview model cardDocumented inputs
Gemini 3 Pro
Not sourced
Hy4 preview
Not sourced
Documented outputs
Gemini 3 Pro
Not sourced
Hy4 preview
Not sourced
Provider availability
Gemini 3 Pro
Not sourced
Hy4 preview
Not sourced
Reasoning profile
Gemini 3 Pro
Non-Reasoning
Hy4 preview
Reasoning
Weight access
Gemini 3 Pro
Proprietary
Hy4 preview
Open Weight
License
Gemini 3 Pro
Proprietary
Hy4 preview
Open Weight
Release date
Gemini 3 Pro
2025-11-18
Hy4 preview
2026-08-28
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
- Hy4 preview has the higher public point estimate, 60.86 versus 60.62. Their conditional score ranges overlap. These ranges do not establish rank confidence.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- Gemini 3 Pro has the larger documented window (2M).
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, Gemini 3 Pro or Hy4 preview?
Hy4 preview has the higher public point estimate, 60.86 versus 60.62. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, Gemini 3 Pro or Hy4 preview?
Hy4 preview scores higher for coding on the public lane, 57.1 to 43.2. Gemini 3 Pro 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.
Which is better for agentic tasks, Gemini 3 Pro or Hy4 preview?
Gemini 3 Pro is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
Which costs less, Gemini 3 Pro or Hy4 preview?
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Which has the larger context window, Gemini 3 Pro or Hy4 preview?
Gemini 3 Pro has the larger documented context window: 2M, compared with 1M.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence56 rows
Agentic
Gert Labs
Gemini 3 Pro63.23%SourceHy4 preview—Not directly comparable
JobBench
Gemini 3 Pro11.4%SourceHy4 preview61.7%SourceHy4 preview leads this result
Terminal-Bench 2.1
Gemini 3 Pro—Hy4 preview85.4%SourceNot directly comparable
CyberGym
Gemini 3 Pro—Hy4 preview78.4%SourceNot directly comparable
WideResearch
Gemini 3 Pro—Hy4 preview83.9%SourceNot directly comparable
DRACO
Gemini 3 Pro—Hy4 preview77.2%SourceNot directly comparable
MCP Atlas
Gemini 3 Pro—Hy4 preview83.7%SourceNot directly comparable
Toolathlon-Verified
Gemini 3 Pro—Hy4 preview74.1%SourceNot directly comparable
APEX-Agents
Gemini 3 Pro—Hy4 preview37.1%SourceNot directly comparable
skillsBench
Gemini 3 Pro—Hy4 preview62.9%SourceNot directly comparable
Agents' Last Exam
Gemini 3 Pro—Hy4 preview22.8%SourceNot directly comparable
AutomationBench
Gemini 3 Pro—Hy4 preview32.1%SourceNot directly comparable
BankerToolBench
Gemini 3 Pro—Hy4 preview78.6%SourceNot directly comparable
HLE w/ tools
Gemini 3 Pro—Hy4 preview55.4%SourceNot directly comparable
Terminal-Bench 2.1 (Vals)
Gemini 3 Pro—Hy4 preview55.1%SourceNot directly comparable
CWE-bench v1
Gemini 3 Pro—Hy4 preview53.0%SourceNot directly comparable
Coding
Vibe Code Bench
Gemini 3 Pro14.30%SourceHy4 preview—Not directly comparable
Terminal-Bench 2.1
Gemini 3 Pro—Hy4 preview85.4%SourceNot directly comparable
SWE-bench Pro
Gemini 3 Pro—Hy4 preview65.7%SourceNot directly comparable
SWE Multilingual
Gemini 3 Pro—Hy4 preview82.9%SourceNot directly comparable
DeepSWE
Gemini 3 Pro—Hy4 preview64.3%SourceNot directly comparable
NL2Repo
Gemini 3 Pro—Hy4 preview58.9%SourceNot directly comparable
ProgramBench
Gemini 3 Pro—Hy4 preview17.5%SourceNot directly comparable
PostTrain Bench
Gemini 3 Pro—Hy4 preview35.6%SourceNot directly comparable
sweMarathon
Gemini 3 Pro—Hy4 preview31.9%SourceNot directly comparable
Reasoning
Multimodal
MMMU
Gemini 3 Pro87.2%SourceHy4 preview—Not directly comparable
MMMU-Pro
Gemini 3 Pro81%SourceHy4 preview—Not directly comparable
RealWorldQA
Gemini 3 Pro83.3%SourceHy4 preview—Not directly comparable
OmniDocBench 1.5
Gemini 3 Pro88.5%SourceHy4 preview—Not directly comparable
Video-MME (with subtitle)
Gemini 3 Pro88.4%SourceHy4 preview—Not directly comparable
Video-MME (w/o subtitle)
Gemini 3 Pro87.7%SourceHy4 preview—Not directly comparable
MathVision
Gemini 3 Pro86.6%SourceHy4 preview—Not directly comparable
We-Math
Gemini 3 Pro86.9%SourceHy4 preview—Not directly comparable
DynaMath
Gemini 3 Pro85.1%SourceHy4 preview—Not directly comparable
SimpleVQA
Gemini 3 Pro73.2%SourceHy4 preview—Not directly comparable
MMLongBench-Doc
Gemini 3 Pro60.5%SourceHy4 preview—Not directly comparable
CC-OCR
Gemini 3 Pro79.0%SourceHy4 preview—Not directly comparable
AI2D_TEST
Gemini 3 Pro94.1%SourceHy4 preview—Not directly comparable
CountBench
Gemini 3 Pro97.3%SourceHy4 preview—Not directly comparable
RefCOCO (avg)
Gemini 3 Pro84.1%SourceHy4 preview—Not directly comparable
ODINW13
Gemini 3 Pro46.3%SourceHy4 preview—Not directly comparable
ERQA
Gemini 3 Pro70.5%SourceHy4 preview—Not directly comparable
VideoMMMU
Gemini 3 Pro87.6%SourceHy4 preview—Not directly comparable
MLVU (M-Avg)
Gemini 3 Pro83.0%SourceHy4 preview—Not directly comparable
ScreenSpot Pro
Gemini 3 Pro72.7%SourceHy4 preview—Not directly comparable
CharXiv
Gemini 3 Pro81.4%SourceHy4 preview—Not directly comparable
V*
Gemini 3 Pro88.0%SourceHy4 preview—Not directly comparable
OfficeQA Pro
Gemini 3 Pro—Hy4 preview66.2%SourceNot directly comparable
Knowledge
Math
Apex
Gemini 3 Pro—Hy4 preview74.2%SourceNot directly comparable
56 public results · 1 shared
Watch Gemini 3 Pro vs Hy4 preview
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 5,500+ readers.
Last updated October 13, 2026