Agentic
Not comparable- Gemini 3.7 Flash
- 64.0
- Supported · #12/152
- MiniCPM5-2B
- Not ranked
- Basis
- BenchAlign lane · 6 vs 2 public rows
- Reading
- Not comparable
Gemini 3.7 Flash vs MiniCPM5-2B
Updated September 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
2 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.
Long documents
Prompts that approach the documented context limit
Gemini 3.7 Flash
Gemini 3.7 Flash has the larger documented context window.
Confidence: documented
Show secondary and unsupported calls
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
MiniCPM5-2B is not ranked on the public lane for coding, so no winner is named for coding.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
MiniCPM5-2B is not ranked on the public lane for agentic, so no winner is named for agentic.
Confidence: limited
Chat 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-rates
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. MiniCPM5-2B does not fit this workload in one request. MiniCPM5-2B has no comparable published API token rate.
Confidence: listed-rates
Repository 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
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
20 Gemini 3.7 Flash only
2 Shared
17 MiniCPM5-2B only
- Shared results
- 2
- Gemini 3.7 Flash only
- 20
- MiniCPM5-2B only
- 17
- Like-for-like categories
- 0 / 8
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.
Coding
Not comparable- Gemini 3.7 Flash
- 62.7
- Supported · #15/151
- MiniCPM5-2B
- Not ranked
- Basis
- BenchAlign lane · 6 vs 5 public rows
- Reading
- Not comparable
Reasoning
Not comparable- Gemini 3.7 Flash
- 77.2
- Unranked · 3 rankable rows
- MiniCPM5-2B
- Not ranked
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Knowledge
Not comparable- Gemini 3.7 Flash
- 69.7
- Supported · #13/183
- MiniCPM5-2B
- Not ranked
- Basis
- BenchAlign lane · 6 vs 5 public rows
- Reading
- Not comparable
Math
Not comparable- Gemini 3.7 Flash
- Not ranked
- MiniCPM5-2B
- Not ranked
- Basis
- Provisional lane · 0 vs 2 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Gemini 3.7 Flash
- Not ranked
- MiniCPM5-2B
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Gemini 3.7 Flash
- 82.7
- #9/48
- MiniCPM5-2B
- Not ranked
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Gemini 3.7 Flash
- Not ranked
- MiniCPM5-2B
- Not ranked
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
| Category | Gemini 3.7 Flash | MiniCPM5-2B | Basis | Reading |
|---|---|---|---|---|
| Agentic | 64.0Supported · #12/152 | Not ranked | Not comparableBenchAlign lane · 6 vs 2 public rows | Not comparable |
| Coding | 62.7Supported · #15/151 | Not ranked | Not comparableBenchAlign lane · 6 vs 5 public rows | Not comparable |
| Reasoning | 77.2Unranked · 3 rankable rows | Not ranked | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Knowledge | 69.7Supported · #13/183 | Not ranked | Not comparableBenchAlign lane · 6 vs 5 public rows | Not comparable |
| Math | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 2 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | 82.7#9/48 | Not ranked | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 1 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
- Gemini 3.7 Flash
- $0.00262
- Fits in one request
- MiniCPM5-2B
- Self-hosted; infrastructure cost varies
- Fits in one request
MiniCPM5-2B has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Gemini 3.7 Flash
- $0.04875
- Fits in one request
- MiniCPM5-2B
- Self-hosted; infrastructure cost varies
- Fits in one request
MiniCPM5-2B has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Gemini 3.7 Flash
- $0.0675
- Fits in one request
- MiniCPM5-2B
- Self-hosted; infrastructure cost varies
- Does not fit in one request
- Cached-input rate unavailable
MiniCPM5-2B does not fit this workload in one request. MiniCPM5-2B has no comparable published API token rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationGemini 3.7 FlashMiniCPM5-2B
Context window
Maximum documented context; output-token limits may be lower.
Gemini 3.7 Flash
MiniCPM5-2B
API model ID
Gemini 3.7 Flash
gemini-3.7-flash
Google Gemini 3.7 Flash API documentationMiniCPM5-2B
openbmb/MiniCPM5-2B
OpenBMB MiniCPM5-2B model cardCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Gemini 3.7 Flash
$0.075 per 1M cached input tokens
Google Gemini API pricingMiniCPM5-2B
No comparable hosted API rate
OpenBMB MiniCPM5-2B model cardDocumented inputs
Gemini 3.7 Flash
text, image, video, audio, pdf
Google Gemini 3.7 Flash API documentationMiniCPM5-2B
Not sourced
Documented outputs
Gemini 3.7 Flash
MiniCPM5-2B
Not sourced
Provider availability
Gemini 3.7 Flash
Generally Available · Gemini API, Google AI Studio, Gemini App - Spark, Gemini Enterprise App, Gemini Enterprise Agent Platform, Google Antigravity
Google DeepMind Gemini 3.7 Flash model cardMiniCPM5-2B
Not sourced
Reasoning profile
Gemini 3.7 Flash
Reasoning
MiniCPM5-2B
Reasoning
Weight access
Gemini 3.7 Flash
Proprietary
MiniCPM5-2B
Open Weight
License
Gemini 3.7 Flash
Proprietary
MiniCPM5-2B
Open Weight
Release date
Gemini 3.7 Flash
2026-08-13
MiniCPM5-2B
2026-09-06
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
- At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- Gemini 3.7 Flash has the larger documented window (1M).
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 evidence39 rows
Agentic
Terminal-Bench 2.1
Gemini 3.7 Flash85.8%SourceMiniCPM5-2B8.6%SourceGemini 3.7 Flash leads this result
Terminal-Bench 3.0
Gemini 3.7 Flash14.9%SourceMiniCPM5-2B—Not directly comparable
AutomationBench
Gemini 3.7 Flash30.4%SourceMiniCPM5-2B—Not directly comparable
OSWorld 2.0
Gemini 3.7 Flash47.9%SourceMiniCPM5-2B—Not directly comparable
Agents' Last Exam
Gemini 3.7 Flash26.3%SourceMiniCPM5-2B—Not directly comparable
Terminal-Bench 2.1 (Vals)
Gemini 3.7 Flash77.5%SourceMiniCPM5-2B—Not directly comparable
BFCL v4
Gemini 3.7 Flash—MiniCPM5-2B66.6%SourceNot directly comparable
Coding
FrontierCode 1.1 Main
Gemini 3.7 Flash43.6%SourceMiniCPM5-2B—Not directly comparable
DeepSWE
Gemini 3.7 Flash65.3%SourceMiniCPM5-2B—Not directly comparable
Terminal-Bench 2.1
Gemini 3.7 Flash85.8%SourceMiniCPM5-2B8.6%SourceGemini 3.7 Flash leads this result
FrontierSWE v2
Gemini 3.7 Flash20.3%SourceMiniCPM5-2B—Not directly comparable
LiveCodeBench (Vals)
Gemini 3.7 Flash88.7%SourceMiniCPM5-2B—Not directly comparable
SWE-bench (Vals)
Gemini 3.7 Flash80.8%SourceMiniCPM5-2B—Not directly comparable
LiveCodeBench v6
Gemini 3.7 Flash—MiniCPM5-2B69.1%SourceNot directly comparable
SciCode
Gemini 3.7 Flash—MiniCPM5-2B26.3%SourceNot directly comparable
SWE-bench Verified
Gemini 3.7 Flash—MiniCPM5-2B46.4%SourceNot directly comparable
SWE-bench Pro
Gemini 3.7 Flash—MiniCPM5-2B14.4%SourceNot directly comparable
Reasoning
Knowledge
HLE-Verified
Gemini 3.7 Flash53.6%SourceMiniCPM5-2B—Not directly comparable
LABBench2
Gemini 3.7 Flash82.1%SourceMiniCPM5-2B—Not directly comparable
BioMysteryBench (human-solvable)
Gemini 3.7 Flash87.1%SourceMiniCPM5-2B—Not directly comparable
BioMysteryBench (human-difficult)
Gemini 3.7 Flash43.5%SourceMiniCPM5-2B—Not directly comparable
GPQA Diamond (Vals)
Gemini 3.7 Flash93.9%SourceMiniCPM5-2B—Not directly comparable
MMLU-Pro (Vals)
Gemini 3.7 Flash90.1%SourceMiniCPM5-2B—Not directly comparable
MMLU-Pro
Gemini 3.7 Flash—MiniCPM5-2B70.8%SourceNot directly comparable
MMLU-Redux
Gemini 3.7 Flash—MiniCPM5-2B84.7%SourceNot directly comparable
HLE
Gemini 3.7 Flash—MiniCPM5-2B8.9%SourceNot directly comparable
GPQA-D
Gemini 3.7 Flash—MiniCPM5-2B70.2%SourceNot directly comparable
SuperGPQA
Gemini 3.7 Flash—MiniCPM5-2B40.8%SourceNot directly comparable
Math
Multimodal
Instruction following
Frequently asked questions
Which is better, Gemini 3.7 Flash or MiniCPM5-2B?
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, Gemini 3.7 Flash or MiniCPM5-2B?
MiniCPM5-2B is not ranked on the public lane for coding, so no winner is named for coding.
Which is better for agentic tasks, Gemini 3.7 Flash or MiniCPM5-2B?
MiniCPM5-2B is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
Which costs less, Gemini 3.7 Flash or MiniCPM5-2B?
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 3.7 Flash or MiniCPM5-2B?
Gemini 3.7 Flash has the larger documented context window: 1M, compared with 131K.
Related comparisons
Last updated September 10, 2026
Watch Gemini 3.7 Flash vs MiniCPM5-2B
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.