Model comparison
Gemma 4 31B vs GPT-5.1-Codex
Head-to-head evidence from 13 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Gemma 4 31B #43 (Supported); GPT-5.1-Codex #99 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Gemma 4 31B and GPT-5.1-Codex share 13 comparable benchmark results. 0 of 8 categories are comparable. 16 results are unique to Gemma 4 31B; 3 to GPT-5.1-Codex.
Updated July 23, 2026- Shared results
- 13
- Gemma 4 31B only
- 16
- GPT-5.1-Codex only
- 3
- Comparable categories
- 0 / 8
Benchmark data for Gemma 4 31B and GPT-5.1-Codex is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 13 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-5.1-Codex has the larger context window at 400K, compared with 256K for Gemma 4 31B.
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 | Gemma 4 31B | Δ | GPT-5.1-Codex |
|---|---|---|---|
| Coding | Gemma 4 31B41.6 | MarginNo overlap | GPT-5.1-CodexNot measured |
| Knowledge | Gemma 4 31B52.9 | MarginNo overlap | GPT-5.1-CodexNot measured |
| Multimodal | Gemma 4 31B76.9 | MarginNo overlap | GPT-5.1-CodexNot measured |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Gemma 4 31B | GPT-5.1-Codex | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Gemma 4 31B$0 input / $0 output | GPT-5.1-CodexNot available | A complete price comparison is not available. |
| Generation speedtokens per second | Gemma 4 31BNot available | GPT-5.1-CodexNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Gemma 4 31BNot available | GPT-5.1-CodexNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Gemma 4 31B256K | GPT-5.1-Codex400K | GPT-5.1-Codex lists the larger context window. |
Benchmark Deep Dive
Agentic10 benchmarks
| Benchmark | Gemma 4 31B | GPT-5.1-Codex | Result |
|---|---|---|---|
| AA Agentic IndexSource | 14.4% | — | Not comparable |
| τ²-bench resultsSource | 59.9% | 83% | GPT-5.1-Codex leads |
| GDPval-AASource | 15.2% | — | Not comparable |
| GDPval-AASource | 804 | — | Not comparable |
| Gert LabsSource | 35.26% | 49.68% | GPT-5.1-Codex leads |
| AA EnterpriseOps-GymSource | 28.3% | — | Not comparable |
| AA ITBenchSource | 37.3% | — | Not comparable |
| AA Tau3 BankingSource | 15.1% | — | Not comparable |
| terminalBenchHardSource | 36.4% | — | Not comparable |
| JobBenchSource | — | 26.2% | Not comparable |
Coding5 benchmarks
Reasoning2 benchmarks
Knowledge11 benchmarks
| Benchmark | Gemma 4 31B | GPT-5.1-Codex | Result |
|---|---|---|---|
| GPQASource | 84.3% | — | Not comparable |
| MMLU-ProSource | 85.2% | — | Not comparable |
| HLESource | 26.5% | — | Not comparable |
| HLE w/o toolsSource | 19.5% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 29.4% | 34.7% | GPT-5.1-Codex leads |
| AA-GPQA DiamondSource | 85.7% | 86.0% | GPT-5.1-Codex leads |
| AA-HLESource | 22.7% | 23.4% | GPT-5.1-Codex leads |
| AA-Omniscience IndexSource | -45.4% | -6.0% | GPT-5.1-Codex leads |
| AA-Omniscience AccuracySource | 19.9% | 39.2% | GPT-5.1-Codex leads |
| AA-Omniscience Hallucination RateSource | 81.6% | 74.4% | GPT-5.1-Codex leads |
| AA Openness IndexSource | 38.9% | — | Not comparable |
Multimodal3 benchmarks
Inst. Following1 benchmarks
| Benchmark | Gemma 4 31B | GPT-5.1-Codex | Result |
|---|---|---|---|
| AA-IFBenchSource | 75.6% | 70.0% | Gemma 4 31B leads |
Frequently Asked Questions (3)
Can I compare Gemma 4 31B and GPT-5.1-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 Gemma 4 31B and GPT-5.1-Codex today?
Gemma 4 31B: $0.00 input / $0.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
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.