Skip to main content

Model comparison

Mistral Medium 3.5 128B vs Step 3.7 Flash

Data verified

Head-to-head evidence from 18 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Margin
10.2pts
← winning
50.76/100
1 category wins0 category wins

BenchAlign evidence: Mistral Medium 3.5 128B not scored; Step 3.7 Flash estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Mistral Medium 3.5 128B and Step 3.7 Flash share 18 comparable benchmark results. 1 of 8 categories are comparable. 6 results are unique to Mistral Medium 3.5 128B; 12 to Step 3.7 Flash.

Updated July 16, 2026
Shared results
18
Mistral Medium 3.5 128B only
6
Step 3.7 Flash only
12
Comparable categories
1 / 8

Pick Mistral Medium 3.5 128B if you want the stronger benchmark profile. Step 3.7 Flash only becomes the better choice if you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 18 shared benchmark results across 6 evidence categories; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Mistral Medium 3.5 128B is clearly ahead on the provisional aggregate, 61 to 57. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Mistral Medium 3.5 128B's sharpest advantage is in coding, where it averages 77.6 against 56.3.

Mistral Medium 3.5 128B is also the more expensive model on tokens at $1.50 input / $7.50 output per 1M tokens, versus $0.20 input / $1.15 output per 1M tokens for Step 3.7 Flash. That is roughly 6.5x on output cost alone.

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 Mistral Medium 3.5 128B and Step 3.7 Flash
CategoryMistral Medium 3.5 128BΔStep 3.7 Flash
CodingMistral Medium 3.5 128B77.6Margin 21.3Step 3.7 Flash56.3
AgenticMistral Medium 3.5 128BNot measuredMarginNo overlapStep 3.7 Flash66.4

Operational comparison

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

MetricMistral Medium 3.5 128BStep 3.7 FlashComparison
Input / output priceUSD per 1M tokensMistral Medium 3.5 128B$1.5 input / $7.5 outputStep 3.7 Flash$0.2 input / $1.15 outputStep 3.7 Flash has the lower combined listed price.
Generation speedtokens per secondMistral Medium 3.5 128BNot availableStep 3.7 FlashNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenMistral Medium 3.5 128BNot availableStep 3.7 FlashNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensMistral Medium 3.5 128B256KStep 3.7 Flash256KListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkMistral Medium 3.5 128BStep 3.7 FlashResult
τ³-bench resultsSource 91.4%Not comparable
AA Agentic IndexSource 19.0%21.5%Step 3.7 Flash leads
τ²-bench resultsSource 94.2%98.5%Step 3.7 Flash leads
GDPval-AASource 21.4%25.9%Step 3.7 Flash leads
GDPval-AASource 9291017Step 3.7 Flash leads
Gert LabsSource 39.10%51.57%Step 3.7 Flash leads
AA EnterpriseOps-GymSource 33.7%Not comparable
AA Harvey LABSource 0.8%Not comparable
AA Tau3 BankingSource 14.4%Not comparable
Terminal-Bench 2.0Source 59.5%Not comparable
BrowseCompSource 75.8%Not comparable
DeepSearchQASource 92.8%Not comparable
ToolathlonSource 49.5%Not comparable
Claw-EvalSource 67.1%Not comparable
HLE w/ toolsSource 47.2%Not comparable
APEX-Agents-AASource 14.8%Not comparable
CodingMistral Medium 3.5 128B wins
BenchmarkMistral Medium 3.5 128BStep 3.7 FlashResult
SWE-bench VerifiedSource 77.6%Not comparable
AA Coding IndexSource 46.9%39.6%Mistral Medium 3.5 128B leads
Terminal-Bench HardSource 33.3%35.6%Step 3.7 Flash leads
AA-SciCodeSource 39.6%40.0%Step 3.7 Flash leads
SWE-bench ProSource 56.3%Not comparable
Terminal-Bench 2.0Source 59.5%Not comparable
Reasoning
BenchmarkMistral Medium 3.5 128BStep 3.7 FlashResult
AA-LCRSource 61.0%63.7%Step 3.7 Flash leads
CritPtSource 0.0%2.3%Step 3.7 Flash leads
Knowledge
BenchmarkMistral Medium 3.5 128BStep 3.7 FlashResult
Artificial Analysis Intelligence IndexSource 29.9%30.3%Step 3.7 Flash leads
AA-GPQA DiamondSource 74.8%80.9%Step 3.7 Flash leads
AA-HLESource 12.8%19.9%Step 3.7 Flash leads
AA-Omniscience IndexSource -36.3%-37.5%Mistral Medium 3.5 128B leads
AA-Omniscience AccuracySource 25.1%25.4%Step 3.7 Flash leads
AA-Omniscience Hallucination RateSource 82.0%84.4%Mistral Medium 3.5 128B leads
AA Openness IndexSource 33.3%Not comparable
Multimodal
BenchmarkMistral Medium 3.5 128BStep 3.7 FlashResult
AA-MMMU-ProSource 64.9%75.3%Step 3.7 Flash leads
SimpleVQASource 79.2%Not comparable
V*Source 95.3%Not comparable
Design Arena WebsiteSource 1218Not comparable
Inst. Following
BenchmarkMistral Medium 3.5 128BStep 3.7 FlashResult
AA-IFBenchSource 68.8%67.3%Mistral Medium 3.5 128B leads
Frequently Asked Questions (2)

Which is better, Mistral Medium 3.5 128B or Step 3.7 Flash?

Mistral Medium 3.5 128B is ahead on BenchLM's provisional leaderboard, 61 to 57.

Which is better for coding, Mistral Medium 3.5 128B or Step 3.7 Flash?

Mistral Medium 3.5 128B has the edge for coding in this comparison, averaging 77.6 versus 56.3. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 16, 2026

The AI models change fast. We track them for you.

A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.