Home Nvidia’s GeForce GTX 980 Ti graphics card reviewed
Reviews

Nvidia’s GeForce GTX 980 Ti graphics card reviewed

Scott Wasson Former Editor-in-Chief Author expertise
Disclosure
Disclosure
In our content, we occasionally include affiliate links. Should you click on these links, we may earn a commission, though this incurs no additional cost to you. Your use of this website signifies your acceptance of our terms and conditions as well as our privacy policy.

The Tech Report Why Trust Tech Report Arrow down

Tech Report is one of the oldest hardware, news, and tech review sites on the internet. We write helpful technology guides, unbiased product reviews, and report on the latest tech and crypto news. We maintain editorial independence and consider content quality and factual accuracy to be non-negotiable.

You knew it was coming. When Nvidia introduced the GeForce GTX Titan X back in March, it was only a matter of time before a slightly slower, less expensive version of that graphics card hit the market. That’s pretty much how it always happens, and this year’s model is no exception.

Behold, the GeForce GTX 980 Ti:

Drawing on my vast reserve of historical knowledge, I can tell you that the “Ti” at the end of that name ostensibly stands for “Titanium.” Look a little closer at the specs for this product, though, and you’ll notice that it might as well stand for “Titan.” The GTX 980 Ti is more of a slightly de-tuned Titan X than a hopped-up GeForce GTX 980.

The GTX 980 Ti is based on the GM200 graphics chip, just like the Titan X, and the spec sheet lists the same base and boost clock speed for both cards. The 980 Ti comes with two modest reductions: only 22 of the GM220’s possible 24 shader multiprocessor units are enabled, and the card has “only” 6GB of GDDR5 memory onboard. That’s it for the cuts, and they’re mostly painless. The 980 Ti still has the same polygon throughput and memory bandwidth as a Titan X, with only a tad less texture filtering and computational power.

Well, kinda. You see, Nvidia has further tuned the GM200 GPU on the 980 Ti, and it expects slighty higher operating clock speeds (~20Hz out of ~1000MHz) as a result. So the difference between the first run of Titan X cards and this newcomer is even smaller in practice than the specs sheet suggests.

Not to worry, rich kids: brand-new Titan X cards now ship with this same tuning, so you can still be ultimate by ordering a new Titan X. (Or, you know, pushing the little slider around in an overclocking utility.)

GPU
base
clock
(MHz)
GPU
boost
clock
(MHz)
ROP
pixels/
clock
Texels
filtered/
clock
Shader
pro-
cessors
Memory
path
(bits)
GDDR5
transfer
rate
Memory
size
Peak
power
draw
E-tail
price
GTX
960
1126 1178 32 64 1024 128 7 GT/s 2 GB 120W $199.99
GTX
970
1050 1178 56 104 1664 224+32 7 GT/s 3.5+0.5GB 145W $329.99
GTX
980
1126 1216 64 128 2048 256 7 GT/s 4 GB 165W $499.99
GTX 980 Ti 1002 1075 96 176 2816 384 7 GT/s 6 GB 250W $649.99
Titan
X
1002 1075 96 192 3072 384 7 GT/s 12 GB 250W $999.99

The table above shows the revised GeForce lineup, and you’ll notice that the GTX 980 Ti lists for $649.99. That’s a nice discount from the one-grand price of the Titan X, especially considering how similar the two products really are. The GTX 980 Ti will come with a copy of Batman: Arkham Knight, as well. That’s not exactly a bargain, but it’s a way better deal than the $1K flagship.

Speaking of which, to make room for the 980 Ti, Nvidia has also dropped the price of the vanilla GeForce GTX 980 by 50 bucks to $499.99.

Beyond that basic info, there’s not much more to say about this new GeForce. The board is rated for 250W of peak power draw, so Nvidia recommends a 600W PSU for the host system. You’ll need one eight-pin PCIe aux power lead and one six-pin lead in order to power the card.

As you can see, our review unit comes with Nvidia’s standard silver-and-black reference cooler with light-up green lettering across the top. I still like the looks of it, and the cooler’s performance is pretty solid, although the Titan X’s black-out paint job is easier on the eyes, in my estimation.

Nvidia is releasing a little bit of other news today to go along with the GTX 980 Ti’s introduction. Among those tidbits is an update on G-Sync and some new software tech for virtual reality game development, which I’ve covered separately. Now, let’s see how this puppy performs.

Our testing methods
Most of the numbers you’ll see on the following pages were captured with Fraps, a software tool that can record the rendering time for each frame of animation. We sometimes use a tool called FCAT to capture exactly when each frame was delivered to the display, but that’s usually not necessary in order to get good data with single-GPU setups. We have, however, filtered our Fraps results using a three-frame moving average. This filter should account for the effect of the three-frame submission queue in Direct3D. If you see a frame time spike in our results, it’s likely a delay that would affect when the frame reaches the display.

We didn’t use Fraps with Civ: Beyond Earth or Battlefield 4. Instead, we captured frame times directly from the game engines using the games’ built-in tools. We didn’t use our low-pass filter on those results.

As ever, we did our best to deliver clean benchmark numbers. Our test systems were configured like so:

Processor Core i7-5960X
Motherboard Gigabyte
X99-UD5 WiFi
Chipset Intel X99
Memory size 16GB (4 DIMMs)
Memory type Corsair
Vengeance LPX
DDR4 SDRAM at 2133 MT/s
Memory timings 15-15-15-36
2T
Chipset drivers INF update
10.0.20.0
Rapid Storage Technology Enterprise 13.1.0.1058
Audio Integrated
X79/ALC898
with Realtek 6.0.1.7246 drivers
Hard drive Kingston
SSDNow 310 960GB SATA
Power supply Corsair
AX850
OS Windows
8.1 Pro
Driver
revision
GPU
base
core clock
(MHz)
GPU
boost
clock
(MHz)
Memory
clock
(MHz)
Memory
size
(MB)
Asus
Radeon
R9 290X
Catalyst 15.4/15.5
betas
1050 1350 4096
Radeon
R9 295 X2
Catalyst 15.4/15.5
betas
1018 1250 8192
GeForce
GTX 780 Ti
GeForce 352.90 876 928 1750 3072
Gigabyte
GeForce GTX 980
GeForce 352.90 1228 1329 1753 4096

GeForce GTX 980 Ti
GeForce
352.90
1002 1076 1753 6144
GeForce
Titan X
GeForce 352.90 1002 1076 1753 12288

Thanks to Intel, Corsair, Kingston, and Gigabyte for helping to outfit our test rigs with some of the finest hardware available. AMD, Nvidia, and the makers of the various products supplied the graphics cards for testing, as well.

Also, our FCAT video capture and analysis rig has some pretty demanding storage requirements. For it, Corsair has provided four 256GB Neutron SSDs, which we’ve assembled into a RAID 0 array for our primary capture storage device. When that array fills up, we copy the captured videos to our RAID 1 array, comprised of a pair of 4TB Black hard drives provided by WD.

Unless otherwise specified, image quality settings for the graphics cards were left at the control panel defaults. Vertical refresh sync (vsync) was disabled for all tests.

The tests and methods we employ are generally publicly available and reproducible. If you have questions about our methods, hit our forums to talk with us about them.

Sizing ’em up
Do the math involving the clock speeds and per-clock potency of the latest high-end graphics cards, and you’ll end up with a comparative table that looks something like this:

Peak pixel
fill rate
(Gpixels/s)
Peak
bilinear
filtering
int8/fp16
(Gtexels/s)
Peak
rasterization
rate
(Gtris/s)
Peak
shader
arithmetic
rate
(tflops)
Memory
bandwidth
(GB/s)
Asus
R9 290X
67 185/92 4.2 5.9 346
Radeon
R9 295 X2
130 358/179 8.1 11.3 640
GeForce GTX
780 Ti
37 223/223 4.6 5.3 336
Gigabyte
GTX 980
85 170/170 5.3 5.4 224
GeForce
GTX 980 Ti
95 189/189 6.5 6.1 336
GeForce
Titan X
103 206/206 6.5 6.6 336

Those are the peak capabilities of each of these cards, in theory. Our shiny new Beyond3D GPU architecture suite measures true delivered performance using a series of directed tests.

The GTX 980 Ti lands squarely in the middle between the GTX 980 and the Titan X in terms of pixel fill rate, which is what we’d expect given the theoretical rates in the table above. Notice that the 980 Ti’s peak rate is lower than the Titan X’s even though it has the same ROP count (96 pixels per clock) and clock speed. That’s because, on recent Nvidia GPUs, fill rate can be limited by the number of shader multiprocessors and rasterizers. The GTX 980 Ti’s 22 SMs can only transfer 88 pixels per clock to the ROPs, so its peak throughput is a bit lower than the Titan X’s.

This test nicely illustrates the impact of color compression on memory bandwidth. Newer GeForces based on the Maxwell architecture are able to extract substantially more throughput from the easily compressible black texture than the Kepler-based GTX 780 Ti does.

Meanwhile, as Andrew Lauritzen pointed out to us, the Radeon R9 290X doesn’t show any compression benefits in this test because it’s primarily limited by its ROP throughput. We may have to rejigger this test to sidestep that ROP limitation. I suspect, if we did so, we’d see some benefits from color compression on the Radeon, as well.

Most of these GPUs come incredibly close to matching their peak theoretical filtering rates in this test, the GTX 980 Ti included.

The GeForce cards all somewhat exceed their theoretical peaks in the polygon throughput test. My best guess is that they’re able to operate at higher-than-usual clock speeds during this directed test—either that or they’re warping the fabric of space and time, but I don’t think that feature has been implemented yet.

Looks to me like the GTX 980 Ti is also exceeding its “GPU Boost” clock in our ALU math test, where it scores slightly higher than its 6.1 teraflops theoretical max. Nvidia’s Boost clock is just a typical operating speed, not a maximum frequency, so this isn’t a huge surprise. Notice, though, that the Titan X tops out at exactly 6.7 teraflops, no higher than expected. The 980 Ti’s lower GPU voltage probably gives it an edge over our early-model Titan X.

Project Cars
Project Cars is beautiful. I could race around Road America in a Formula C car for hours and be thoroughly entertained, too. In fact, that’s pretty much what I did in order to test these graphics cards.


Click the buttons above to cycle through the plots. Each card’s frame times are from one of the three test runs we conducted for that card. You’ll see that the frame rendering times for the GTX 980 Ti are nice and consistently low, always below about 25 milliseconds, even though we’re testing at 4K with some pretty intensive image quality settings. The plots for most of the GeForce cards look similar.

Switch over to the Radeon plots, and things look a little rougher. That’s true even though I tested this game with the latest Catalyst 15.5 beta drivers with specific optimizations for Project Cars. The R9 290X doesn’t look bad—just a bit slow overall, really—but the R9 295 X2 is another story. The R9 295 X2 is a dual-GPU monstrosity with water cooling that is arguably the GTX 980 Ti’s closest competition from AMD. The X2’s dual GPUs make it generally faster than the 290X, but this card somehow runs into some trouble in the middle of our test run. In fact, we encountered the same issue across multiple test runs.

Granted, we’re testing with Fraps, which measures early in the frame production pipeline, not with FCAT, which measures frame delivery to the screen. (I’d prefer to test with FCAT but haven’t been able to get it working at 4K resolutions.) AMD’s frame-pacing solution might smooth the delivery of frames to the screen and produce a bit smoother line than you see in the plot above, but it can’t fix those larger delays.

In fact, you can feel this slowdown while playing on the 295 X2. It happens in a specific section of the track, a long straight where the car is pointed into the sun.

The R9 295 X2 matches the GTX 980 Ti in average FPS, but we know than the 980 Ti’s frame delivery is much smoother overall. That fact is captured by our frame-time-sensitive 99th percentile metric.

We can understand in-game animation fluidity even better by looking at the entire “tail” of the frame time distribution for each card, which illustrates what happens with the most difficult frames.

The 980 Ti and the 295 X2 generally perform the same, but the Radeon struggles with the last five to 10 percent of frames that prove challenging for whatever reason.


These “time spent beyond X” graphs are meant to show “badness,” those instances where animation may be less than fluid—or at least less than perfect. The 50-ms threshold is the most notable one, since it corresponds to a 20-FPS average. We figure if you’re not rendering any faster than 20 FPS, even for a moment, then the user is likely to perceive a slowdown. 33 ms correlates to 30 FPS or a 30Hz refresh rate. Go beyond that with vsync on, and you’re into the bad voodoo of quantization slowdowns. And 16.7 ms correlates to 60 FPS, that golden mark that we’d like to achieve (or surpass) for each and every frame.

The 295 X2 spends some time beyond the 33-ms mark, as does the R9 290X. None of the GeForces do.

The Witcher 3
Performance in this game has been the subject of some contention, so I tried to be judicious in selecting my test settings. I tested the Radeons with the just-released Catalyst 15.5 beta drivers, and all cards were tested with the latest 1.04 patch for the game. Following AMD’s recommendations for achieving good CrossFire performance, I set “EnableTemporalAA=false” in the game’s config file when testing the Radeon R9 295 X2. And, as you’ll see below, I disabled Nvidia’s HairWorks entirely in order to avoid the associated performance pitfalls.


The Maxwell-based 9-series GeForce cards all perform well here, but the GTX 780 Ti and the Radeons struggle a bit. Notice that we’re not even testing at 4K.

Once again, the R9 295 X2 would seem to perform well based on its FPS average, but the frame-time plots and the 99th percentile tell a different tale. As you can see in the curve below, the 295 X2 struggles with the last five percent or so of frames. We know from the plot and from play-testing that those slowdowns are distributed throughout the duration of our test session, with the most trouble coming in the first third or so. The 295 X2’s performance isn’t horrible, but it doesn’t deliver smooth gaming to match the GTX 980, let alone the 980 Ti.

The GTX 980 Ti remains a very close match for the Titan X. In fact, their frame time curves are nearly right on top of one another in the image above.


The R9 295 X2 does perform well generally, as indicated by the fact that it spends less time beyond 16-ms threshold than the 980 Ti. But it does spend time beyond the 50-ms threshold, and the Maxwell-based GeForces don’t.

GTA V
Forgive me for the massive number of screenshots below, but GTA V has a ton of image quality settings. I more or less cranked them all up in order to stress these high-end video cards. Truth be told, most or all of these cards can run GTA V quite fluidly at lower settings in 4K—and it still looks quite nice. You don’t need a $500+ graphics card to get solid performance from this game in 4K, not unless you push all the quality sliders to the right.



Finally, we have a game where the R9 295 X2 seems to live up to its considerable potential. The X2’s lead over the GTX 980 Ti isn’t as dramatic as the FPS average would seem to indicate, though, if you look at the 99th percentile frame times. Also, the GTX 980 Ti somehow edges out the Titan X here by a smidgen, perhaps due to slightly higher operating clock speeds.

Far Cry 4



The R9 295 X2’s performance in Far Cry 4 is much improved from the basket case is was in our Titan X review.

As for the 980 Ti, it’s almost an exact match for the Titan X; its orange curve is entirely covered by the Titan X’s in the plot above.

Alien: Isolation



No surprises here. The cards all perform well, and they finish pretty much in the order one might expect.

Civilization: Beyond Earth
Since this game’s built-in benchmark simply spits out frame times, we were able to give it a full workup without having to resort to manual testing. That’s nice, since manual benchmarking of an RTS with zoom is kind of a nightmare.

Oh, and the Radeons were tested with the Mantle API instead of Direct3D. Only seemed fair, since the game supports it.



This is an incredibly close match-up between the top three cards, with no clear winner. The 295 X2 is using the Mantle graphics API and a load-balancing method called split-frame rendering in order to divvy up the work between its two GPUs. SFR is preferable to the usual method, AFR, for a number of techie reasons. SFR doesn’t yield abnormally high FPS averages, but it can produce a better user experience, with more instant responses to user inputs. Interestingly, when the X2 teams its two big Hawaii GPUs together, it delivers approximately the same performance as one GM200 GPU aboard the GTX 980 Ti.

Battlefield 4
We tested BF4 on the Radeons using the Mantle API, since it was available.



Once again, with Mantle and proper load-balancing, the 295 X2’s two Hawaii GPUs almost exactly equal the performance of a single GM200 GPU aboard the GTX 980 Ti or Titan X.

Crysis 3



This is an odd one. The R9 295 X2 is clearly the fastest card overall, yet it spends the most time beyond the 50-ms threshold thanks to a few distinct slowdowns during the test session. My subjective sense is that the GM200-based GeForces feel smoother overall, although we’re kind of splitting hairs at this point.

Power consumption
Please note that our “under load” tests aren’t conducted in an absolute peak scenario. Instead, we have the cards running a real game, Crysis 3, in order to show us power draw with a more typical workload.

Here’s where we figure out why the R9 295 X2 isn’t really a very good foil for the GTX 980 Ti. When equipped with the X2 and its two big Hawaii GPUs, our test rig draws more than twice the power at the wall socket than it does with a GTX 980 Ti. We’re measuring power draw in Crysis 3—and as we’ve just noted, the GTX 980 Ti and the 295 X2 deliver very similar performance in this game. The power efficiency implications are pretty clear.

Noise levels and GPU temperatures
These video card coolers are so good, they’re causing us testing problems. You see, the noise floor in Damage Labs is about 35-36 dBA. It varies depending on things I can’t quite pinpoint, but one notable contributor is the noise produced by the lone cooling fan always spinning on our test rig, the 120-mm fan on the CPU cooler. Anyhow, what you need to know is that any of the noise results that range below 36 dBA are running into the limits of what we can test accurately. Don’t make too much of differences below that level.

The GTX 980 Ti draws a bit less power under load than the Titan X, and as a result, it doesn’t push the Nvidia reference cooler quite as hard. The result is a small reduction in noise levels under load. The 295 X2 isn’t that much louder than the 980 Ti, at the end of the day, but it manages that feat by combining a longer card with an external radiator for its water cooler.

Conclusions
As usual, we’ll sum up our test results with a couple of value scatter plots. The best values tend toward the upper left corner of each plot, where performance is highest and prices are lowest. We’ve converted our 99th-percentile frame time results into FPS, so that higher is better, in order to make this work.


The GeForce GTX 980 Ti fits neatly into Nvidia’s current lineup, offering nearly the same performance as the Titan X at a considerable discount. If you were salivating over a Titan X but decided to wait for the less expensive version, your patience has been rewarded.

The matchup between the GTX 980 Ti and its closest competitor, the Radeon R9 295 X2, is a strangely close mismatch. The R9 295 X2 clearly has more raw GPU horsepower, as demonstrated by its commanding lead in terms of FPS averages across the eight games we tested. Yet the X2 can’t always turn that additional power into a fluid gaming experience, which is why the 980 Ti ever-so-slightly surpasses it in our 99th percentile frame time metric. The dual-GPU Radeon’s performance is somewhat brittle, and it’s too often troublesome in recently released games.

The R9 295 X2 also consumes a heckuva lot of power, more than double that of a GTX 980 Ti when installed in the same system. To give you a sense of the disparity, have a look at this scatter plot of power efficiency in Crysis 3. The most efficient solutions will tend toward the top left portion of the plot.

These results are from just one game, but they illustrate how effectively Nvidia has managed to improve power efficiency with its Maxwell architecture. The GTX 980 Ti continues that tradition and leaves AMD at a distinct disadvantage. I can’t imagine choosing an R9 295 X2 over a GTX 980 Ti right now.

Then again, prospective buyers may want to wait a few weeks, because AMD is preparing its own next-gen GPU, code-named Fiji, to do battle with the GM200. We already know Fiji will feature an innovative memory type, known as HBM, that promises quite a bit more throughput than any of Nvidia’s current products. That advantage could make Fiji rather formidable when all is said and done. At the very least, things are about to get interesting. Nvidia has played a strong hand, and now it’s up to AMD to counter.

Enjoy our work? Pay what you want to subscribe and support us.

The Tech Report - Editorial ProcessOur Editorial Process

The Tech Report editorial policy is centered on providing helpful, accurate content that offers real value to our readers. We only work with experienced writers who have specific knowledge in the topics they cover, including latest developments in technology, online privacy, cryptocurrencies, software, and more. Our editorial policy ensures that each topic is researched and curated by our in-house editors. We maintain rigorous journalistic standards, and every article is 100% written by real authors.

Scott Wasson Former Editor-in-Chief

Scott Wasson Former Editor-in-Chief

Scott Wasson is a veteran in the tech industry and the former Editor-in-Chief at Tech Report. With a laser focus on tech product reviews, Wasson's expertise shines in evaluating CPUs and graphics cards, and much more.

Latest News

Apple’s New Safari Ad Takes a Dig at Rivals, Especially Google Chrome
News

Apple’s New Safari Ad Takes a Dig at Rivals, Especially Google Chrome

446.40% $SHIB Burnt After WazirX Security Breach – Shiba Shootout Nears $700K Milestone
Crypto News

446.40% $SHIB Burnt After WazirX Security Breach – Shiba Shootout Nears $700K Milestone

Wazir X (India’s largest crypto exchange) suffered a serious security breach on July 18, with $5T Shiba Inu ($SHIB) stolen, among other cryptocurrencies.  After the news broke, $SHIB’s price plummeted...

Microsoft’s Biggest Global Outage: Everything You Need To Know
News

Microsoft’s Biggest Global Outage: Everything You Need to Know

A global outage of Microsoft’s beloved Windows software has brought almost half the world to a standstill. From airports to supermarkets and banking services, many crucial day-to-day services have been...

Shiba Inu Team Says Upcoming P2E Game Is Significant for SHIB, BONE, and Shibarium Ecosystems
Crypto News

Shiba Inu Team Says Upcoming P2E Game Is Significant for SHIB, BONE, and Shibarium Ecosystems

OTC Markets Overwhelm CEX Markets as New Wallets Amassed Over 1.45M Bitcoin Tokens This Year
Crypto News

OTC Markets Overwhelm CEX Markets as New Wallets Amassed Over 1.45M Bitcoin Tokens This Year

Brad Garlinghouse Reveals Ripple Will Buy Back $1.4 Billion Worth of Stock as IPO Approaches
Crypto News

Brad Garlinghouse Reveals Ripple Will Buy Back $1.4 Billion Worth of Stock as IPO Approaches

Bitcoin BTC's Tight Bollinger Bands Reveal $190,000 as Next Possible Price Target
Crypto News

Bitcoin BTC’s Tight Bollinger Bands Reveal $190,000 as Next Possible Price Target