Model comparison
Gemini 2.5 Flash-Lite vs Grok 4.3
Grok 4.3 is the stronger model overall, scoring 43.8 to 37.0 on the Noometry Index. Gemini 2.5 Flash-Lite costs 8.9× less per token, which makes it the better buy when Grok 4.3's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
GoogleSummary
- They share 23 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 1 category and Grok 4.3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 4.3 leads 52.5 to 32.5.
- The biggest single-benchmark swing is DTBench: 62.8% for Gemini 2.5 Flash-Lite and 90.7% for Grok 4.3.
- Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $1.25 / $2.50 for Grok 4.3.
- Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 1M.
Side by side
| Gemini 2.5 Flash-Lite | Grok 4.3 | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 37.0 | 43.8 |
| Released | 2025-06-17 | 2026-04-17 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 66K | 30K |
| Input $ / M tokens | $0.10 | $1.25 |
| Output $ / M tokens | $0.40 | $2.50 |
| Results tracked | 33 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.3 leads
Gemini 2.5 Flash-Lite: 38.5 (#173), Grok 4.3: 41.6 (#121)
| Benchmark | Gemini 2.5 Flash-Lite | Grok 4.3 |
|---|---|---|
| WeirdML | 35.2% | 49.9% |
| LMArena Coding | 1373 | 1415 |
| ALE-Bench | 325.9 | 944.17 |
| LMArena WebDev | — | 1357 |
| SciCode | — | 47.3% |
Agentic & Tool Use Too close to call
Gemini 2.5 Flash-Lite: 28.0 (#96), Grok 4.3: 27.7 (#99)
| Benchmark | Gemini 2.5 Flash-Lite | Grok 4.3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 36.9% | — |
| GDP.pdf | — | 8% |
| LMArena Search | — | 1165 |
| Vending-Bench 2 | — | 35.26 |
Reasoning Grok 4.3 leads
Gemini 2.5 Flash-Lite: 22.2 (#205), Grok 4.3: 35.9 (#68)
| Benchmark | Gemini 2.5 Flash-Lite | Grok 4.3 |
|---|---|---|
| LMArena Hard Prompts | 1377 | 1396 |
| DTBench | 62.8% | 90.7% |
| LMCA | 18.1% | 38.3% |
| Epoch Capabilities Index | 133.94 | 149.16 |
| Kagi LLM Benchmark | 40.5% | — |
| NYT Connections (extended) | — | 55.2% |
| CritPt | — | 8% |
| Chess Puzzles | — | 25% |
| ForecastBench | — | 60.3 |
Math Grok 4.3 leads
Gemini 2.5 Flash-Lite: 38.0 (#144), Grok 4.3: 46.0 (#74)
| Benchmark | Gemini 2.5 Flash-Lite | Grok 4.3 |
|---|---|---|
| LMArena Math | 1373 | 1388 |
| FrontierMath (Tiers 1-3) | — | 42.8% |
| FrontierMath Tier 4 | — | 14.6% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| ProofBench | — | 11% |
| Omni-MATH | 48% | — |
Knowledge Grok 4.3 leads
Gemini 2.5 Flash-Lite: 32.5 (#210), Grok 4.3: 52.5 (#62)
| Benchmark | Gemini 2.5 Flash-Lite | Grok 4.3 |
|---|---|---|
| LMArena Expert | 1373 | 1385 |
| GPQA Diamond | — | 88.8% |
| SimpleQA Verified | — | 33.2% |
| MMLU-Pro | 53.7% | — |
| Vectara Hallucination Rate | 3.3% | — |
| GPQA (HELM) | 30.9% | — |
Multimodal Grok 4.3 leads
Gemini 2.5 Flash-Lite: 29.1 (#114), Grok 4.3: 31.6 (#104)
| Benchmark | Gemini 2.5 Flash-Lite | Grok 4.3 |
|---|---|---|
| LMArena Vision | 1198 | 1229 |
| VPCT | 30% | — |
| Blueprint-Bench 2 | — | 0% |
Multilingual Grok 4.3 leads
Gemini 2.5 Flash-Lite: 49.3 (#134), Grok 4.3: 50.5 (#120)
| Benchmark | Gemini 2.5 Flash-Lite | Grok 4.3 |
|---|---|---|
| LMArena Non-English | 1369 | 1385 |
| LMArena Chinese | 1404 | 1422 |
| LMArena French | 1388 | 1412 |
| LMArena German | 1389 | 1395 |
| LMArena Japanese | 1359 | 1379 |
| LMArena Korean | 1360 | 1356 |
| LMArena Russian | 1373 | 1399 |
| LMArena Spanish | 1396 | 1398 |
Instruction Following Grok 4.3 leads
Gemini 2.5 Flash-Lite: 70.0 (#168), Grok 4.3: 72.1 (#140)
| Benchmark | Gemini 2.5 Flash-Lite | Grok 4.3 |
|---|---|---|
| LMArena Instruction Following | 1367 | 1366 |
| IFEval | 81% | — |
Long Context Grok 4.3 leads
Gemini 2.5 Flash-Lite: 33.3 (#262), Grok 4.3: 42.5 (#123)
| Benchmark | Gemini 2.5 Flash-Lite | Grok 4.3 |
|---|---|---|
| LMArena Longer Query | 1373 | 1393 |
| Fiction.LiveBench | 47.2% | — |
Writing & Preference Grok 4.3 leads
Gemini 2.5 Flash-Lite: 56.8 (#135), Grok 4.3: 58.5 (#118)
| Benchmark | Gemini 2.5 Flash-Lite | Grok 4.3 |
|---|---|---|
| LMArena Text | 1379 | 1397 |
| LMArena Creative Writing | 1367 | 1380 |
| LMArena Multi-Turn | 1366 | 1406 |
| WildBench | 81.8% | — |
| EQ-Bench 4 | — | 1075 |
Frequently asked questions
Is Gemini 2.5 Flash-Lite better than Grok 4.3?
Grok 4.3 is the stronger model overall, scoring 43.8 to 37.0 on the Noometry Index. Gemini 2.5 Flash-Lite costs 8.9× less per token, which makes it the better buy when Grok 4.3's lead doesn't matter for your workload.
Which is cheaper, Gemini 2.5 Flash-Lite or Grok 4.3?
Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Grok 4.3 lists at $1.25 and $2.50.
Is Gemini 2.5 Flash-Lite or Grok 4.3 better for coding?
Grok 4.3 scores higher on coding benchmarks: 41.6 versus 38.5 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash-Lite does, with 1.05M tokens against 1M.
How many benchmarks do Gemini 2.5 Flash-Lite and Grok 4.3 share?
23 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Grok 4.3 has 40.