Model comparison
Gemini 3.1 Flash-Lite vs GPT-5.3 Codex
Head-to-head evidence from 14 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Gemini 3.1 Flash-Lite #111 (Supported); GPT-5.3 Codex #26 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Gemini 3.1 Flash-Lite and GPT-5.3 Codex share 14 comparable benchmark results. 0 of 8 categories are comparable. 6 results are unique to Gemini 3.1 Flash-Lite; 7 to GPT-5.3 Codex.
Updated July 20, 2026- Shared results
- 14
- Gemini 3.1 Flash-Lite only
- 6
- GPT-5.3 Codex only
- 7
- Comparable categories
- 0 / 8
Benchmark data for Gemini 3.1 Flash-Lite and GPT-5.3 Codex is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 14 shared benchmark results across 6 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.
GPT-5.3 Codex is priced at $1.75 input / $14.00 output per 1M tokens, versus $0.25 input / $1.50 output per 1M tokens for Gemini 3.1 Flash-Lite. Gemini 3.1 Flash-Lite has the larger context window at 1M, compared with 400K for GPT-5.3 Codex.
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 | Gemini 3.1 Flash-Lite | Δ | GPT-5.3 Codex |
|---|---|---|---|
| Agentic | Gemini 3.1 Flash-LiteNot measured | MarginNo overlap | GPT-5.3 Codex71.4 |
| Coding | Gemini 3.1 Flash-LiteNot measured | MarginNo overlap | GPT-5.3 Codex67.2 |
| Multimodal | Gemini 3.1 Flash-Lite73.2 | MarginNo overlap | GPT-5.3 CodexNot measured |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Gemini 3.1 Flash-Lite | GPT-5.3 Codex | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Gemini 3.1 Flash-Lite$0.25 input / $1.5 output | GPT-5.3 Codex$1.75 input / $14 output | Gemini 3.1 Flash-Lite has the lower combined listed price. |
| Generation speedtokens per second | Gemini 3.1 Flash-Lite205 tok/s | GPT-5.3 Codex79 tok/s | Gemini 3.1 Flash-Lite has the higher measured throughput. |
| First-answer latencyseconds to first token | Gemini 3.1 Flash-Lite7.50 s | GPT-5.3 Codex88.26 s | Gemini 3.1 Flash-Lite reaches the first token sooner. |
| Context windowmaximum listed tokens | Gemini 3.1 Flash-Lite1M | GPT-5.3 Codex400K | Gemini 3.1 Flash-Lite lists the larger context window. |
Benchmark Deep Dive
Agentic9 benchmarks
| Benchmark | Gemini 3.1 Flash-Lite | GPT-5.3 Codex | Result |
|---|---|---|---|
| AA Agentic IndexSource | 6.2% | — | Not comparable |
| APEX-Agents-AASource | 12.2% | — | Not comparable |
| τ²-bench resultsSource | 31.3% | 86% | GPT-5.3 Codex leads |
| GDPval-AASource | 7.1% | — | Not comparable |
| GDPval-AASource | 642 | — | Not comparable |
| Gert LabsSource | 38.46% | 57.47% | GPT-5.3 Codex leads |
| Terminal-Bench 2.0Source | — | 77.3% | Not comparable |
| OSWorld-VerifiedSource | — | 64.7% | Not comparable |
| JobBenchSource | — | 33.7% | Not comparable |
Coding6 benchmarks
| Benchmark | Gemini 3.1 Flash-Lite | GPT-5.3 Codex | Result |
|---|---|---|---|
| Vibe Code BenchSource | 0.00% | 61.77% | GPT-5.3 Codex leads |
| AA Coding IndexSource | 34.7% | — | Not comparable |
| AA-SciCodeSource | 41.9% | 53.2% | GPT-5.3 Codex leads |
| SWE-bench VerifiedSource | — | 85% | Not comparable |
| SWE-bench ProSource | — | 56.8% | Not comparable |
| SWE-RebenchSource | — | 58.2% | Not comparable |
Reasoning2 benchmarks
Knowledge6 benchmarks
| Benchmark | Gemini 3.1 Flash-Lite | GPT-5.3 Codex | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 25.0% | 44.3% | GPT-5.3 Codex leads |
| AA-GPQA DiamondSource | 82.2% | 91.5% | GPT-5.3 Codex leads |
| AA-HLESource | 16.2% | 39.9% | GPT-5.3 Codex leads |
| AA-Omniscience IndexSource | -15.5% | 9.9% | GPT-5.3 Codex leads |
| AA-Omniscience AccuracySource | 36.4% | 51.8% | GPT-5.3 Codex leads |
| AA-Omniscience Hallucination RateSource | 81.6% | 86.9% | Gemini 3.1 Flash-Lite leads |
Multimodal3 benchmarks
Inst. Following1 benchmarks
| Benchmark | Gemini 3.1 Flash-Lite | GPT-5.3 Codex | Result |
|---|---|---|---|
| AA-IFBenchSource | 77.2% | 75.4% | Gemini 3.1 Flash-Lite leads |
Frequently Asked Questions (3)
Can I compare Gemini 3.1 Flash-Lite and GPT-5.3 Codex on BenchLM yet?
Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.
Why does this comparison show “coming soon”?
BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.
What data is available for Gemini 3.1 Flash-Lite and GPT-5.3 Codex today?
Gemini 3.1 Flash-Lite: $0.25 input / $1.50 output per 1M tokens GPT-5.3 Codex: $1.75 input / $14.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.
Related Comparisons
Explore More
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.