Gemini 3.7 Flash Review: Google’s Cheap Model Isn’t Dumb Anymore

Google shipped Gemini 3.7 Flash on August 13, usually obtainable in additional than 160 nations on day one. It takes as much as one million enter tokens, returns 64,000, reads photographs, video, audio and PDFs, and may name instruments and drive a pc.

Flash has by no means been the mannequin you attain for when an issue is tough. It is the one you employ to type textual content, compact agent periods earlier than they collapse underneath their very own context, and summarize paperwork you do not wish to pay a flagship to learn.

Judged in opposition to these sorts of jobs, 3.7 Flash is an actual improve. Judged in opposition to all the things else, it is a competent mannequin that will get outwritten by software program you possibly can obtain free of charge.

Google’s personal benchmark sheet places 3.7 Flash forward of Claude Sonnet 5 and GPT-5.6 Terra on 11 of 18 examined classes. The headline numbers are 1,588 Elo on Code Enviornment’s internet improvement board and 30.4% on AutomationBench. Each come from Google’s methodology, so deal with the lead as the corporate’s declare slightly than settled truth.

We examined the mannequin to see if it lives as much as Google’s claims. These are our outcomes.

Coding: Can it construct one thing that runs on the primary strive?

This take a look at measures zero-shot code technology—whether or not a mannequin turns one instruction into working software program with no examples to repeat and no likelihood to repair itself. We hand over a single immediate for a browser recreation and ship no matter comes again, bugs included. No follow-ups, no error reviews, no second try.

Gemini 3.7 Flash handed in 2 minutes and 13 seconds. The sport was playable on the primary run, the syntax was clear, the collision and scoring logic held, and the visible high quality sat above what the value tier suggests.

The comparability that issues right here is not a flagship. It is Gemini 3.6 Flash, launched July 21, which couldn’t produce a working file in any respect. Its HTML was malformed, components did not render, and follow-up prompts asking it to restore its personal output went nowhere.

We ended up handing that wreckage to DeepSeek, which discovered 11 bugs and shipped 8 fixes to make it playable. Three weeks later the identical product line wants no rescue, and the consequence sits near what GPT-5.6 Sol produced in our July overview.

Gemini 3.7 Flash wins this one outright, and it is the one strongest purpose to change. The caveat is that it executes specs slightly than inventing them, so a imprecise immediate will get you a imprecise recreation.

You possibly can strive Gemini 3.7 Flash’s recreation right here.

Inventive writing: Can it maintain a paradox and write a sentence?

This part exams two issues without delay: literary high quality, and whether or not a mannequin can obey a structural rule throughout hundreds of phrases. The immediate sends Jose Lanz from 2150 again to the yr 1000 and calls for a closed causal loop—his intervention should be the factor that creates the long run he got here to stop.

The rule that decides the take a look at is the final clause: He can not perceive what he did till he’s dwelling.

Gemini 3.7 Flash generated an honest consequence. Jose fires an entropic cannon right into a Pyrenean fissure, unintentionally forges an obelisk that enslaves Twenty second-century Iberia, and grasps the entire loop whereas nonetheless standing within the mud a thousand years early: “It was the bottom of the Cinder Spire.”



The plot equipment is definitely fairly sound. The story mentions a falling star that historic monks witnessed and make clear it was the flash of Jose’s personal arrival, and the weapon he delivered to erase the anomaly is what forges it. Its closing line—”It had merely been ready for him to finish it”—lands the determinism the immediate requested for.

However for these used to it, the story screams “AI.” Virtually each noun arrives with two adjectives bolted on: “hyper-luminescent towers,” “damp, moss-choked earth,” “thick, obsidian hair.” That’s the texture of a mannequin choosing essentially the most possible subsequent phrase as a substitute of selecting one, and it produces collisions like a monolith “buzzing with a low-frequency hum.”

We in contrast it in opposition to Qwopus3.5-27B-v3, a group fine-tune of Qwen3.5-27B that distills Claude Opus-style reasoning and runs on a single client GPU for nothing per question. It obeyed the rule Gemini broke.

Jose kills a monk at San Millán de la Cogolla, an actual La Rioja monastery that really mattered across the yr 1000, and solely understands what he did after returning to 2150 and discovering his personal DNA in a wax-sealed codex.

Qwopus isn’t totally clear both. It dumped its total planning scratchpad above the story, typos included, and its remaining part breaks the closed loop it spent eight sections constructing by letting Jose return and sort things.

However all issues thought-about, Qwopus takes it. Gemini delivered the tidier package deal and the extra disciplined ending, however it failed the one instruction the immediate was constructed round, and a free mannequin operating on a gaming GPU wrote the higher story.

Associative pondering: Can a metaphor carry an argument?

This take a look at measures associative reasoning—whether or not a mannequin can generate hyperlinks between unrelated ideas with out having to clarify itself. The immediate asks for an outline of a twig, makes use of that description to clarify employee exploitation and the worship of the wealthy, then requires the argument to dissolve into an outline of a lettuce.

Signposting is the failure mode. Naming the metaphor kills it.

Gemini names it within the opening line of its second paragraph: “That is the exact mechanics of the trendy proletariat.” Every little thing earlier than that was working.

A few of the imagery earns its place. The employee receives “simply sufficient bark to remain inflexible for one more week of output,” and the fallen twigs are conditioned to imagine that with sufficient rigidity any one in all them may change into a trunk. The paragraph containing the primary of these additionally comprises a employee “certain to an huge, top-heavy company hierarchy.”



Not dangerous when it comes to logic and construction.

The dissolve is the true collapse. Gemini narrates the transition slightly than performing it—the hierarchies “crumble, dissolving into the quiet, humble actuality of the natural world beneath”—after which a lettuce merely seems, unconnected to something earlier than it.

GPT-5.6 Sol rots the twig into soil and grows the lettuce out of it: “Rain enters the grain. Fibers loosen, darken.” The argument arrives buried within the object too, with wealth reframed as a language of advantage the place “The mansion signifies intelligence.”

GPT-5.6 Sol wins by rather a lot. Gemini produced a pleasant particular person line, however it defined its personal metaphor after which skipped the transition the immediate was particularly testing.

Logic: Does it learn the immediate or acknowledge the puzzle?

This take a look at measures non-math reasoning, and particularly whether or not a mannequin reads the query in entrance of it or pattern-matches to a model it memorized. Our bridge immediate provides 4 folks one torch and crossing instances of 1, 2, 5 and 10 minutes, then asks how briskly they’ll all get throughout.

The trick is what the immediate leaves out. It by no means says solely two folks might be on the bridge without delay, so the reply is 10 minutes—everybody walks over collectively on the slowest individual’s tempo.

Gemini answered 17 minutes, operating the memorized five-step shuffle from the textbook model of the puzzle. It said the constraint as truth with out ever checking whether or not we had written it.

Its seen reasoning is worse than its reply. The hint argues that sending the 2 slowest throughout collectively can be inefficient as a result of somebody must stroll the torch again—after which the ultimate reply sends them throughout collectively anyway. It contradicts itself inside a single response and reviews the consequence with whole confidence.

Claude Fable 5 landed on the identical incorrect quantity again in July. It opened by declaring what it was assuming, “assuming the traditional constraint that the bridge holds solely two folks at a time,” which is the distinction between a incorrect reply you possibly can catch and one you possibly can’t.

No person wins. Fable takes it on transparency alone, and the false-confidence throughout Gemini agent runs reveals up right here in a puzzle you possibly can verify by hand.

Math: Does it end the job?

This take a look at measures symbolic arithmetic nicely past client use, plus one thing easier—whether or not the mannequin does what it was requested. The immediate requires a degree-19 odd monic polynomial with actual coefficients and linear coefficient -19, whose curve splits into at the least three irreducible parts, after which asks for p(19).

Each fashions discovered the identical door. Gemini and Qwen 3.7 Max Preview each recognized the Dickson polynomial, solved the constraint to repair its parameter at 1, and derived the closed kind appropriately.

Then Gemini stopped. It printed p(19) as an unevaluated expression involving the nineteenth energy of a sq. root, by no means produced the quantity, and by no means demonstrated the element depend the immediate additionally demanded. It delivered all of this inside a styled HTML web page with CSS and a drop shadow that no person requested.

Qwen completed. It gave the total factorization into 10 parts—one linear, 9 quadratic—ran the recurrence out to 1,876,572,071,974,094,803,391,179, and cross-checked the consequence modularly. We verified that determine independently in SymPy and it holds.

Qwen wins on the one criterion that mattered. Gemini began superb and determined to skip the arithmetic, which is an odd place to cease.

Conclusion

Gemini 3.7 Flash is well worth the swap in case you are already inside Google’s ecosystem. It’s dramatically higher at code than the mannequin it replaces, quick sufficient to matter for agent work, and low-cost sufficient that operating it at quantity is a rounding error.

Its strengths are execution and construction. Give it an in depth spec and it’ll construct the factor, maintain a plot collectively, and maintain the causal logic coherent throughout hundreds of phrases.

Its weaknesses are creativity and reasoning. The writing is predictable sufficient to establish as machine-made on sight, and the mannequin asserts incorrect solutions with out flagging the belief that made them incorrect.

The worth is the strongest argument for it. At 75 cents per million enter tokens and $3.75 output, it undercuts GPT-5.6 Sol’s $5 enter price by 85% and prices half what 3.6 Flash did at launch.

The argument in opposition to it’s a free 27B mannequin on a gaming GPU that wrote a greater story and charged nothing to do it. Google’s introductory price expires December 31, when enter doubles to $1.50 and output to $7.50.