Skip to main content

Model comparison

GLM-4.7 vs MiMo-V2-Flash

Data verified

Head-to-head evidence from 19 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

61.16/100
Margin
7.1pts
← winning
54.06/100
1 category wins1 category wins

Public leaderboard positions: GLM-4.7 #42 (Supported); MiMo-V2-Flash #91 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. GLM-4.7 and MiMo-V2-Flash share 19 comparable benchmark results. 2 of 8 categories are comparable. 11 results are unique to GLM-4.7; 0 to MiMo-V2-Flash.

Updated July 20, 2026
Shared results
19
GLM-4.7 only
11
MiMo-V2-Flash only
0
Comparable categories
2 / 8

Pick GLM-4.7 if you want the stronger benchmark profile. MiMo-V2-Flash only becomes the better choice if knowledge is the priority or you need the larger 256K context window.

Confidence note. This is a partial-evidence comparison with 19 shared benchmark results across 6 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

GLM-4.7 is clearly ahead on the BenchAlign aggregate, 61.16 to 54.06. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GLM-4.7's sharpest advantage is in coding, where it averages 75.4 against 73.4. The single biggest benchmark swing on the page is GPQA, 85.7% to 83.7%. MiMo-V2-Flash does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.

MiMo-V2-Flash gives you the larger context window at 256K, compared with 200K for GLM-4.7.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for GLM-4.7 and MiMo-V2-Flash
CategoryGLM-4.7ΔMiMo-V2-Flash
KnowledgeGLM-4.751.8Margin 32.9MiMo-V2-Flash84.7
CodingGLM-4.775.4Margin 2.0MiMo-V2-Flash73.4
AgenticGLM-4.745.7MarginNo overlapMiMo-V2-FlashNot measured
MathGLM-4.71.8MarginNo overlapMiMo-V2-FlashNot measured

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · GLM-4.7B · MiMo-V2-Flash
  1. GPQA

    Knowledge
    Source ↗
    A 85.7%B 83.7%
    Winner: GLM-4.7Δ 2
    GPQA: GLM-4.7 scored 85.7%; MiMo-V2-Flash scored 83.7%. GLM-4.7 wins this benchmark.
  2. MMLU-Pro

    Knowledge
    Source ↗
    A 84.3%B 84.9%
    Winner: MiMo-V2-FlashΔ 0.6
    MMLU-Pro: GLM-4.7 scored 84.3%; MiMo-V2-Flash scored 84.9%. MiMo-V2-Flash wins this benchmark.
  3. SWE-bench Verified

    Coding
    Source ↗
    A 73.8%B 73.4%
    Winner: GLM-4.7Δ 0.4
    SWE-bench Verified: GLM-4.7 scored 73.8%; MiMo-V2-Flash scored 73.4%. GLM-4.7 wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricGLM-4.7MiMo-V2-FlashComparison
Input / output priceUSD per 1M tokensGLM-4.7$0 input / $0 outputMiMo-V2-Flash$0 input / $0 outputListed prices are equal.
Generation speedtokens per secondGLM-4.782 tok/sMiMo-V2-Flash129 tok/sMiMo-V2-Flash has the higher measured throughput.
First-answer latencyseconds to first tokenGLM-4.71.10 sMiMo-V2-Flash2.14 sGLM-4.7 reaches the first token sooner.
Context windowmaximum listed tokensGLM-4.7200KMiMo-V2-Flash256KMiMo-V2-Flash lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkGLM-4.7MiMo-V2-FlashResult
Terminal-Bench 2.0Source 41%Not comparable
BrowseCompSource 52%Not comparable
VITA-BenchSource 15.5%Not comparable
AA Agentic IndexSource 25.4%12.0%GLM-4.7 leads
τ²-bench resultsSource 95.9%83.9%GLM-4.7 leads
Gert LabsSource 39.95%Not comparable
GDPval-AASource 33.3%16.7%GLM-4.7 leads
GDPval-AASource 1165833GLM-4.7 leads
CodingGLM-4.7 wins
BenchmarkGLM-4.7MiMo-V2-FlashResult
SWE-bench VerifiedSource 73.8%73.4%GLM-4.7 leads
LiveCodeBenchSource 84.9%Not comparable
SWE-RebenchSource 58.7%Not comparable
AA Coding IndexSource 45.3%49.8%MiMo-V2-Flash leads
AA-SciCodeSource 45.1%25.9%GLM-4.7 leads
AA LiveCodeBenchSource 89.4%Not comparable
Reasoning
BenchmarkGLM-4.7MiMo-V2-FlashResult
AA-LCRSource 64.0%31.3%GLM-4.7 leads
CritPtSource 1.7%0.0%GLM-4.7 leads
KnowledgeMiMo-V2-Flash wins
BenchmarkGLM-4.7MiMo-V2-FlashResult
GPQASource 85.7%83.7%GLM-4.7 leads
MMLU-ProSource 84.3%84.9%MiMo-V2-Flash leads
HLESource 24.8%Not comparable
Artificial Analysis Intelligence IndexSource 33.7%24.7%GLM-4.7 leads
AA-GPQA DiamondSource 85.9%65.6%GLM-4.7 leads
AA-HLESource 25.1%8.0%GLM-4.7 leads
AA-Omniscience IndexSource -34.6%-48.5%GLM-4.7 leads
AA-Omniscience AccuracySource 29.3%15.2%GLM-4.7 leads
AA-Omniscience Hallucination RateSource 90.3%75.1%MiMo-V2-Flash leads
Math
BenchmarkGLM-4.7MiMo-V2-FlashResult
AIME 2025Source 95.7%94.1%GLM-4.7 leads
FrontierMath v2 (Tiers 1-3)Source 2.439%Not comparable
FrontierMath v2 (Tier 4)Source 0.000%Not comparable
Multimodal
BenchmarkGLM-4.7MiMo-V2-FlashResult
Design Arena WebsiteSource 1258Not comparable
Inst. Following
BenchmarkGLM-4.7MiMo-V2-FlashResult
AA-IFBenchSource 67.9%39.9%GLM-4.7 leads
Frequently Asked Questions (3)

Which is better, GLM-4.7 or MiMo-V2-Flash?

GLM-4.7 is ahead on BenchLM's BenchAlign leaderboard, 61.16 to 54.06. The biggest single separator in this matchup is GPQA, where the scores are 85.7% and 83.7%.

Which is better for knowledge tasks, GLM-4.7 or MiMo-V2-Flash?

MiMo-V2-Flash has the edge for knowledge tasks in this comparison, averaging 84.7 versus 51.8. Inside this category, AA-GPQA Diamond is the benchmark that creates the most daylight between them.

Which is better for coding, GLM-4.7 or MiMo-V2-Flash?

GLM-4.7 has the edge for coding in this comparison, averaging 75.4 versus 73.4. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 20, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.